{"url":"/dataset/cityscapes","name":"Cityscapes","full_name":null,"description_markdown":"**Cityscapes** is a large-scale database which focuses on semantic understanding of urban street scenes. It provides semantic, instance-wise, and dense pixel annotations for 30 classes grouped into 8 categories (flat surfaces, humans, vehicles, constructions, objects, nature, sky, and void). The dataset consists of around 5000 fine annotated images and 20000 coarse annotated ones. Data was captured in 50 cities during several months, daytimes, and good weather conditions. It was originally recorded as video so the frames were manually selected to have the following features: large number of dynamic objects, varying scene layout, and varying background.\r\n\r\nSource: [A Review on Deep Learning Techniques Applied to Semantic Segmentation](https://arxiv.org/abs/1704.06857)\r\nImage Source: [https://www.cityscapes-dataset.com/dataset-overview/](https://www.cityscapes-dataset.com/dataset-overview/)","description_withheld":null,"homepage":"https://www.cityscapes-dataset.com/dataset-overview/","introduced_date":"2016-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-cityscapes-dataset-for-semantic-urban","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","first_author":"Marius Cordts","url":null},"license":{"name":"Custom","url":"https://www.cityscapes-dataset.com/license/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"Image Generation","url":"/task/image-generation","datasets_with_task":"/datasets/task/image-generation"},{"name":"2D Semantic Segmentation","url":"/task/2d-semantic-segmentation","datasets_with_task":"/datasets/task/2d-semantic-segmentation"},{"name":"Instance Segmentation","url":"/task/instance-segmentation","datasets_with_task":"/datasets/task/instance-segmentation"},{"name":"Scene Parsing","url":"/task/scene-parsing","datasets_with_task":"/datasets/task/scene-parsing"},{"name":"Image-to-Image Translation","url":"/task/image-to-image-translation","datasets_with_task":"/datasets/task/image-to-image-translation"},{"name":"Depth Estimation","url":"/task/depth-estimation","datasets_with_task":"/datasets/task/depth-estimation"},{"name":"Semi-Supervised Semantic Segmentation","url":"/task/semi-supervised-semantic-segmentation","datasets_with_task":"/datasets/task/semi-supervised-semantic-segmentation"},{"name":"Panoptic Segmentation","url":"/task/panoptic-segmentation","datasets_with_task":"/datasets/task/panoptic-segmentation"},{"name":"Unsupervised Semantic Segmentation","url":"/task/unsupervised-semantic-segmentation","datasets_with_task":"/datasets/task/unsupervised-semantic-segmentation"},{"name":"Domain Generalization","url":"/task/domain-generalization","datasets_with_task":"/datasets/task/domain-generalization"},{"name":"Monocular Depth Estimation","url":"/task/monocular-depth-estimation","datasets_with_task":"/datasets/task/monocular-depth-estimation"},{"name":"Video Prediction","url":"/task/video-prediction","datasets_with_task":"/datasets/task/video-prediction"},{"name":"Federated Learning","url":"/task/federated-learning","datasets_with_task":"/datasets/task/federated-learning"},{"name":"Interactive Segmentation","url":"/task/interactive-segmentation","datasets_with_task":"/datasets/task/interactive-segmentation"},{"name":"Open Vocabulary Semantic Segmentation","url":"/task/open-vocabulary-semantic-segmentation","datasets_with_task":"/datasets/task/open-vocabulary-semantic-segmentation"},{"name":"Multi-Task Learning","url":"/task/multi-task-learning","datasets_with_task":"/datasets/task/multi-task-learning"},{"name":"Unsupervised Semantic Segmentation with Language-image Pre-training","url":"/task/unsupervised-semantic-segmentation-with","datasets_with_task":"/datasets/task/unsupervised-semantic-segmentation-with"},{"name":"Knowledge Distillation","url":"/task/knowledge-distillation","datasets_with_task":"/datasets/task/knowledge-distillation"},{"name":"Weakly-Supervised Semantic Segmentation","url":"/task/weakly-supervised-semantic-segmentation","datasets_with_task":"/datasets/task/weakly-supervised-semantic-segmentation"},{"name":"Edge Detection","url":"/task/edge-detection","datasets_with_task":"/datasets/task/edge-detection"},{"name":"Real-Time Semantic Segmentation","url":"/task/real-time-semantic-segmentation","datasets_with_task":"/datasets/task/real-time-semantic-segmentation"},{"name":"Real-time Instance Segmentation","url":"/task/real-time-instance-segmentation","datasets_with_task":"/datasets/task/real-time-instance-segmentation"},{"name":"Unsupervised Panoptic Segmentation","url":"/task/unsupervised-panoptic-segmentation","datasets_with_task":"/datasets/task/unsupervised-panoptic-segmentation"},{"name":"Video Semantic Segmentation","url":"/task/video-semantic-segmentation","datasets_with_task":"/datasets/task/video-semantic-segmentation"},{"name":"Semi-Supervised Instance Segmentation","url":"/task/semi-supervised-instance-segmentation","datasets_with_task":"/datasets/task/semi-supervised-instance-segmentation"},{"name":"Robust Object Detection","url":"/task/robust-object-detection","datasets_with_task":"/datasets/task/robust-object-detection"},{"name":"Unsupervised Monocular Depth Estimation","url":"/task/unsupervised-monocular-depth-estimation","datasets_with_task":"/datasets/task/unsupervised-monocular-depth-estimation"},{"name":"Overlapped 10-1","url":"/task/overlapped-10-1","datasets_with_task":"/datasets/task/overlapped-10-1"},{"name":"Domain 11-5","url":"/task/domain-11-5","datasets_with_task":"/datasets/task/domain-11-5"},{"name":"Domain 11-1","url":"/task/domain-11-1","datasets_with_task":"/datasets/task/domain-11-1"},{"name":"Domain 1-1","url":"/task/domain-1-1","datasets_with_task":"/datasets/task/domain-1-1"},{"name":"Overlapped 14-1","url":"/task/overlapped-14-1","datasets_with_task":"/datasets/task/overlapped-14-1"}],"languages":[],"variants":["Semi-Supervised Semantic Segmentation on Cityscapes 6.25% labeled","Semi-Supervised Semantic Segmentation on Cityscapes 12.5% labeled","Cityscapes with extra (no coarse labels)","Cityscapes with extra (no coarse)","Cityscapes heterogeneous","Cityscapes 6.25% labeled","Cityscapes 5% labeled","Cityscapes 2% labeled","Cityscapes 128x128","Cityscapes 93 labeled","Cityscapes 10% labeled","Cityscapes","Cityscapes-5K 256x512","Cityscapes-25K 256x512","Cityscapes val","Cityscapes test","Cityscapes Photo-to-Labels","Cityscapes Labels-to-Photo","Cityscapes 50% labeled","Cityscapes 25% labeled","Cityscapes 12.5% labeled","Cityscapes 100 samples labeled"],"data_loaders":[{"repo":"https://github.com/facebookresearch/detectron2","url":"https://detectron2.readthedocs.io/en/latest/tutorials/builtin_datasets.html#expected-dataset-structure-for-cityscapes","frameworks":["pytorch"]},{"repo":"https://github.com/open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection/blob/master/docs/1_exist_data_model.md","frameworks":["pytorch"]},{"repo":"https://github.com/pytorch/vision","url":"https://pytorch.org/vision/stable/datasets.html#torchvision.datasets.Cityscapes","frameworks":["pytorch"]},{"repo":"https://github.com/voxel51/fiftyone","url":"https://docs.voxel51.com/user_guide/dataset_zoo/datasets.html#cityscapes","frameworks":["tf","pytorch"]},{"repo":"https://github.com/open-mmlab/mmsegmentation","url":"https://github.com/open-mmlab/mmsegmentation/blob/master/docs/dataset_prepare.md","frameworks":["pytorch"]},{"repo":"https://github.com/Kaggle/kaggle-api","url":"https://www.kaggle.com/datasets/sakshaymahna/cityscapes-depth-and-segmentation","frameworks":[]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/cityscapes","frameworks":["tf","jax"]},{"repo":"https://github.com/facebookresearch/MaskFormer","url":"https://github.com/facebookresearch/MaskFormer","frameworks":["pytorch"]}],"num_papers_in_archive":3702,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset_variant":"Cityscapes test","rows":105,"metrics":["Mean IoU (class)","Category mIoU"],"first_row_in_archive_order":{"model":"VLTSeg","paper":"/paper/vltseg-simple-transfer-of-clip-based-vision","metrics":{"Mean IoU (class)":"86.4"},"code_links":[{"title":"VLTSeg/VLTSeg","url":"https://github.com/VLTSeg/VLTSeg"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes-val","task":"Semantic Segmentation","dataset_variant":"Cityscapes val","rows":99,"metrics":["mIoU","FPS","Validation mIoU"],"first_row_in_archive_order":{"model":"ViT-P (InternImage-H)","paper":"/paper/the-missing-point-in-vision-transformers-for","metrics":{"mIoU":"87.4"},"code_links":[{"title":"sajjad-sh33/vit-p","url":"https://github.com/sajjad-sh33/vit-p"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/real-time-semantic-segmentation-on-cityscapes","task":"Real-Time Semantic Segmentation","dataset_variant":"Cityscapes test","rows":39,"metrics":["mIoU","Frame (fps)","Time (ms)"],"first_row_in_archive_order":{"model":"PIDNet-L","paper":"/paper/pidnet-a-real-time-semantic-segmentation","metrics":{"Frame (fps)":"31.1(3090)","Time (ms)":"32.2","mIoU":"80.6%"},"code_links":[{"title":"XuJiacong/PIDNet","url":"https://github.com/XuJiacong/PIDNet"},{"title":"Darth-Kronos/PIDNet_TensorRT","url":"https://github.com/Darth-Kronos/PIDNet_TensorRT"},{"title":"hamidriasat/PIDNet","url":"https://github.com/hamidriasat/PIDNet"},{"title":"HengWeiBin/Oil-Polution-Dataset-with-PIDNet","url":"https://github.com/HengWeiBin/Oil-Polution-Dataset-with-PIDNet"},{"title":"Mahmood-Hussain/PIDNetTensorflow","url":"https://github.com/Mahmood-Hussain/PIDNetTensorflow"},{"title":"enot-autodl/lpcv-2023","url":"https://github.com/enot-autodl/lpcv-2023"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/panoptic-segmentation-on-cityscapes-val","task":"Panoptic Segmentation","dataset_variant":"Cityscapes val","rows":37,"metrics":["PQ","PQst","PQth","mIoU","AP","RQ","SQ"],"first_row_in_archive_order":{"model":"ViT-P (OneFormer, InternImage-H)","paper":"/paper/the-missing-point-in-vision-transformers-for","metrics":{"AP":"50.6","PQ":"70.8","mIoU":"85.4"},"code_links":[{"title":"sajjad-sh33/vit-p","url":"https://github.com/sajjad-sh33/vit-p"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-2","task":"Semi-Supervised Semantic Segmentation","dataset_variant":"Cityscapes 12.5% labeled","rows":33,"metrics":["Validation mIoU"],"first_row_in_archive_order":{"model":"UniMatch V2 (DINOv2-B)","paper":"/paper/unimatch-v2-pushing-the-limit-of-semi","metrics":{"Validation mIoU":"84.3%"},"code_links":[{"title":"LiheYoung/UniMatch-V2","url":"https://github.com/LiheYoung/UniMatch-V2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-1","task":"Semi-Supervised Semantic Segmentation","dataset_variant":"Cityscapes 25% labeled","rows":30,"metrics":["Validation mIoU"],"first_row_in_archive_order":{"model":"UniMatch V2 (DINOv2-B)","paper":"/paper/unimatch-v2-pushing-the-limit-of-semi","metrics":{"Validation mIoU":"84.5%"},"code_links":[{"title":"LiheYoung/UniMatch-V2","url":"https://github.com/LiheYoung/UniMatch-V2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/real-time-semantic-segmentation-on-cityscapes-1","task":"Real-Time Semantic Segmentation","dataset_variant":"Cityscapes val","rows":24,"metrics":["mIoU","Frame (fps)","Time (ms)"],"first_row_in_archive_order":{"model":"PIDNet-L","paper":"/paper/pidnet-a-real-time-semantic-segmentation","metrics":{"Frame (fps)":"31.1(3090)","Time (ms)":"32.2","mIoU":"80.9%"},"code_links":[{"title":"XuJiacong/PIDNet","url":"https://github.com/XuJiacong/PIDNet"},{"title":"Darth-Kronos/PIDNet_TensorRT","url":"https://github.com/Darth-Kronos/PIDNet_TensorRT"},{"title":"hamidriasat/PIDNet","url":"https://github.com/hamidriasat/PIDNet"},{"title":"HengWeiBin/Oil-Polution-Dataset-with-PIDNet","url":"https://github.com/HengWeiBin/Oil-Polution-Dataset-with-PIDNet"},{"title":"Mahmood-Hussain/PIDNetTensorflow","url":"https://github.com/Mahmood-Hussain/PIDNetTensorflow"},{"title":"enot-autodl/lpcv-2023","url":"https://github.com/enot-autodl/lpcv-2023"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-8","task":"Semi-Supervised Semantic Segmentation","dataset_variant":"Cityscapes 50% labeled","rows":23,"metrics":["Validation mIoU"],"first_row_in_archive_order":{"model":"UniMatch V2 (DINOv2-B)","paper":"/paper/unimatch-v2-pushing-the-limit-of-semi","metrics":{"Validation mIoU":"85.1%"},"code_links":[{"title":"LiheYoung/UniMatch-V2","url":"https://github.com/LiheYoung/UniMatch-V2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-to-image-translation-on-cityscapes","task":"Image-to-Image Translation","dataset_variant":"Cityscapes Labels-to-Photo","rows":21,"metrics":["mIoU","FID","Accuracy","Class IOU","Per-class Accuracy","Per-pixel Accuracy","LPIPS"],"first_row_in_archive_order":{"model":"DP-SIMS (ConvNext-L)","paper":"/paper/unlocking-pre-trained-image-backbones-for","metrics":{"FID":"38.2","mIoU":"76.3"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-22","task":"Semi-Supervised Semantic Segmentation","dataset_variant":"Cityscapes 6.25% labeled","rows":18,"metrics":["Validation mIoU"],"first_row_in_archive_order":{"model":"UniMatch V2 (DINOv2-B)","paper":"/paper/unimatch-v2-pushing-the-limit-of-semi","metrics":{"Validation mIoU":"83.6"},"code_links":[{"title":"LiheYoung/UniMatch-V2","url":"https://github.com/LiheYoung/UniMatch-V2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/instance-segmentation-on-cityscapes-val","task":"Instance Segmentation","dataset_variant":"Cityscapes val","rows":17,"metrics":["mask AP","AP50","AP"],"first_row_in_archive_order":{"model":"ViT-P (OneFormer, ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained)","paper":"/paper/the-missing-point-in-vision-transformers-for","metrics":{"AP":"49.0","mask AP":"49.0"},"code_links":[{"title":"sajjad-sh33/vit-p","url":"https://github.com/sajjad-sh33/vit-p"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-semantic-segmentation-on","task":"Unsupervised Semantic Segmentation","dataset_variant":"Cityscapes test","rows":14,"metrics":["mIoU","Accuracy","Pixel Accuracy"],"first_row_in_archive_order":{"model":"CUPS","paper":"/paper/scene-centric-unsupervised-panoptic","metrics":{"Accuracy":"83.2 ","mIoU":"26.8"},"code_links":[{"title":"visinf/cups","url":"https://github.com/visinf/cups"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/robust-object-detection-on-cityscapes-1","task":"Robust Object Detection","dataset_variant":"Cityscapes","rows":13,"metrics":["mPC [AP]"],"first_row_in_archive_order":{"model":"FGT (SD-1.5 Backbone)","paper":"/paper/boosting-domain-generalized-and-adaptive","metrics":{"mPC [AP]":"27.4"},"code_links":[{"title":"heboyong/fitness-generalization-transferability","url":"https://github.com/heboyong/fitness-generalization-transferability"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-3","task":"Semi-Supervised Semantic Segmentation","dataset_variant":"Cityscapes 100 samples labeled","rows":13,"metrics":["Validation mIoU"],"first_row_in_archive_order":{"model":"SemiVL (ViT-B/16)","paper":"/paper/semivl-semi-supervised-semantic-segmentation","metrics":{"Validation mIoU":"76.2"},"code_links":[{"title":"google-research/semivl","url":"https://github.com/google-research/semivl"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-3","task":"Unsupervised Semantic Segmentation with Language-image Pre-training","dataset_variant":"Cityscapes val","rows":12,"metrics":["mIoU","pixel accuracy"],"first_row_in_archive_order":{"model":"CorrCLIP","paper":"/paper/corrclip-reconstructing-correlations-in-clip","metrics":{"mIoU":"51.1"},"code_links":[{"title":"zdk258/CorrCLIP","url":"https://github.com/zdk258/CorrCLIP"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/instance-segmentation-on-cityscapes","task":"Instance Segmentation","dataset_variant":"Cityscapes test","rows":11,"metrics":["mask AP"],"first_row_in_archive_order":{"model":"Deep Watershed Transform","paper":"/paper/deep-watershed-transform-for-instance","metrics":{},"code_links":[{"title":"min2209/dwt","url":"https://github.com/min2209/dwt"},{"title":"timothyn617/watershed-transform","url":"https://github.com/timothyn617/watershed-transform"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/panoptic-segmentation-on-cityscapes-test","task":"Panoptic Segmentation","dataset_variant":"Cityscapes test","rows":10,"metrics":["PQ"],"first_row_in_archive_order":{"model":"OneFormer (ConvNeXt-L, single-scale, Mapillary Vistas-Pretrained)","paper":"/paper/oneformer-one-transformer-to-rule-universal","metrics":{"PQ":"68.0"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"SHI-Labs/OneFormer","url":"https://github.com/SHI-Labs/OneFormer"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-1/oneformer"},{"title":"MindCode-4/code-2","url":"https://github.com/MindCode-4/code-2/tree/main/oneformer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/federated-learning-on-cityscapes","task":"Federated Learning","dataset_variant":"Cityscapes heterogeneous","rows":9,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"SiloBN + ASAM","paper":"/paper/improving-generalization-in-federated","metrics":{"mIoU":"49.75"},"code_links":[{"title":"debcaldarola/fedsam","url":"https://github.com/debcaldarola/fedsam"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-semantic-segmentation-on-cityscapes-val","task":"Video Semantic Segmentation","dataset_variant":"Cityscapes val","rows":9,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"TMANet-50","paper":"/paper/temporal-memory-attention-for-video-semantic","metrics":{"mIoU":"80.3"},"code_links":[{"title":"wanghao9610/TMANet","url":"https://github.com/wanghao9610/TMANet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-generation-on-cityscapes","task":"Image Generation","dataset_variant":"Cityscapes","rows":6,"metrics":["FID-10k-training-steps"],"first_row_in_archive_order":{"model":"Projected GAN","paper":"/paper/projected-gans-converge-faster","metrics":{"FID-10k-training-steps":"3.41"},"code_links":[{"title":"autonomousvision/projected_gan","url":"https://github.com/autonomousvision/projected_gan"},{"title":"dome272/ProjectedGAN-pytorch","url":"https://github.com/dome272/ProjectedGAN-pytorch"},{"title":"tsubota-kouga/ProjectedGAN","url":"https://github.com/tsubota-kouga/ProjectedGAN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-to-image-translation-on-cityscapes-1","task":"Image-to-Image Translation","dataset_variant":"Cityscapes Photo-to-Labels","rows":5,"metrics":["Class IOU","Per-class Accuracy","Per-pixel Accuracy"],"first_row_in_archive_order":{"model":"pix2pix","paper":"/paper/image-to-image-translation-with-conditional","metrics":{"Class IOU":"0.32","Per-class Accuracy":"40.0%","Per-pixel Accuracy":"85.0%"},"code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/research/gan"},{"title":"eriklindernoren/PyTorch-GAN","url":"https://github.com/eriklindernoren/PyTorch-GAN"},{"title":"eriklindernoren/Keras-GAN","url":"https://github.com/eriklindernoren/Keras-GAN"},{"title":"tensorpack/tensorpack","url":"https://github.com/tensorpack/tensorpack/tree/master/examples/GAN"},{"title":"affinelayer/Pix2Pix-tensorflow","url":"https://github.com/affinelayer/Pix2Pix-tensorflow"},{"title":"open-mmlab/mmgeneration","url":"https://github.com/open-mmlab/mmgeneration"},{"title":"MaximeVandegar/Papers-in-100-Lines-of-Code","url":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Image_to_Image_Translation_with_Conditional_Adversarial_Nets"},{"title":"yenchenlin/pix2pix-tensorflow","url":"https://github.com/yenchenlin/pix2pix-tensorflow"},{"title":"Mingtzge/2019-CCF-BDCI-OCR-MCZJ-OCR-IdentificationIDElement","url":"https://github.com/Mingtzge/2019-CCF-BDCI-OCR-MCZJ-OCR-IdentificationIDElement"},{"title":"brade31919/SRGAN-tensorflow","url":"https://github.com/brade31919/SRGAN-tensorflow"},{"title":"bupt-ai-cz/LLVIP","url":"https://github.com/bupt-ai-cz/LLVIP"},{"title":"jackaduma/CycleGAN-VC2","url":"https://github.com/jackaduma/CycleGAN-VC2"},{"title":"mrzhu-cool/pix2pix-pytorch","url":"https://github.com/mrzhu-cool/pix2pix-pytorch"},{"title":"Adi-iitd/AI-Art","url":"https://github.com/Adi-iitd/AI-Art"},{"title":"nekitmm/starnet","url":"https://github.com/nekitmm/starnet"},{"title":"ImagingLab/Colorizing-with-GANs","url":"https://github.com/ImagingLab/Colorizing-with-GANs"},{"title":"andrewowens/multisensory","url":"https://github.com/andrewowens/multisensory"},{"title":"zcemycl/Matlab-GAN","url":"https://github.com/zcemycl/Matlab-GAN"},{"title":"PacktPublishing/Hands-On-Image-Generation-with-TensorFlow-2.0","url":"https://github.com/PacktPublishing/Hands-On-Image-Generation-with-TensorFlow-2.0/tree/master/Chapter04"},{"title":"bcmi/Object-Shadow-Generation-Dataset-DESOBA","url":"https://github.com/bcmi/Object-Shadow-Generation-Dataset-DESOBA"},{"title":"awjuliani/Pix2Pix-Film","url":"https://github.com/awjuliani/Pix2Pix-Film"},{"title":"moein-shariatnia/Deep-Learning","url":"https://github.com/moein-shariatnia/Deep-Learning/tree/main/Image%20Colorization%20Tutorial"},{"title":"Lornatang/PyTorch-CycleGAN","url":"https://github.com/Lornatang/PyTorch-CycleGAN"},{"title":"Vious/LBAM_Pytorch","url":"https://github.com/Vious/LBAM_Pytorch"},{"title":"opendot/ml4a-invisible-cities","url":"https://github.com/opendot/ml4a-invisible-cities"},{"title":"znxlwm/pytorch-pix2pix","url":"https://github.com/znxlwm/pytorch-pix2pix"},{"title":"hahahappyboy/GANForCartoon","url":"https://github.com/hahahappyboy/GANForCartoon"},{"title":"CreativeCodingLab/DeepIllumination","url":"https://github.com/CreativeCodingLab/DeepIllumination"},{"title":"unicredit/ganzo","url":"https://github.com/unicredit/ganzo"},{"title":"anh-nn01/Satellite-Imagery-to-Map-Translation-using-Pix2Pix-GAN-framework","url":"https://github.com/anh-nn01/Satellite-Imagery-to-Map-Translation-using-Pix2Pix-GAN-framework"},{"title":"acecreamu/angularGAN","url":"https://github.com/acecreamu/angularGAN"},{"title":"Montia/bw2color","url":"https://github.com/Montia/bw2color"},{"title":"prakashpandey9/BicycleGAN","url":"https://github.com/prakashpandey9/BicycleGAN"},{"title":"rohitkuk/Cartoonify","url":"https://github.com/rohitkuk/Cartoonify"},{"title":"matlab-deep-learning/pix2pix","url":"https://github.com/matlab-deep-learning/pix2pix"},{"title":"DLHacks/pix2pix_PAN","url":"https://github.com/DLHacks/pix2pix_PAN"},{"title":"akanametov/Pix2Pix","url":"https://github.com/akanametov/Pix2Pix"},{"title":"STASYA00/UrbanGen","url":"https://github.com/STASYA00/UrbanGen"},{"title":"soumik12345/Pix2Pix","url":"https://github.com/soumik12345/Pix2Pix"},{"title":"taivu1998/GANime","url":"https://github.com/taivu1998/GANime"},{"title":"yigitgunduc/tensor-to-image","url":"https://github.com/yigitgunduc/tensor-to-image"},{"title":"icon-lab/pflsynth","url":"https://github.com/icon-lab/pflsynth"},{"title":"a-martyn/unet","url":"https://github.com/a-martyn/unet"},{"title":"XavierJiezou/cloud-removal-deploy","url":"https://github.com/XavierJiezou/cloud-removal-deploy"},{"title":"yd8534976/conGAN","url":"https://github.com/yd8534976/conGAN"},{"title":"ml4its/latent-diffusion-model-for-conditional-reservoir-facies-generation","url":"https://github.com/ml4its/latent-diffusion-model-for-conditional-reservoir-facies-generation"},{"title":"AquibPy/Pix2Pix-Conditional-GANs","url":"https://github.com/AquibPy/Pix2Pix-Conditional-GANs"},{"title":"mohit-kaushik/Satellite_To_MapGeneration","url":"https://github.com/mohit-kaushik/Satellite_To_MapGeneration"},{"title":"Baichenjia/Pix2Pix-eager","url":"https://github.com/Baichenjia/Pix2Pix-eager"},{"title":"mohit-kaushik/Pix2PixGAN","url":"https://github.com/mohit-kaushik/Pix2PixGAN"},{"title":"TanyaChutani/Pix2pix-Tf2.x","url":"https://github.com/TanyaChutani/Pix2pix-Tf2.x"},{"title":"CristianLazoQuispe/skin-lesion-segmentation-using-pix2pix","url":"https://github.com/CristianLazoQuispe/skin-lesion-segmentation-using-pix2pix"},{"title":"linxi159/GAN-training-tricks","url":"https://github.com/linxi159/GAN-training-tricks"},{"title":"xingchenzhao/deep-learning-team-project","url":"https://github.com/xingchenzhao/deep-learning-team-project"},{"title":"xingchenzhao/Generating-Human-Skeletons-with-Mutual-Actions-WGAN-Pytorch","url":"https://github.com/xingchenzhao/Generating-Human-Skeletons-with-Mutual-Actions-WGAN-Pytorch"},{"title":"ashura1234/soccer-line-detection","url":"https://github.com/ashura1234/soccer-line-detection"},{"title":"cianfrocco-lab/GAN-for-Cryo-EM-image-denoising","url":"https://github.com/cianfrocco-lab/GAN-for-Cryo-EM-image-denoising"},{"title":"philip-brohan/weather2weather","url":"https://github.com/philip-brohan/weather2weather"},{"title":"isrugeek/semcolour","url":"https://github.com/isrugeek/semcolour"},{"title":"jaingaurav3/GAN-Hacks","url":"https://github.com/jaingaurav3/GAN-Hacks"},{"title":"deepware/pix2pix","url":"https://github.com/deepware/pix2pix"},{"title":"r06922019/butt_lion_paper_notes","url":"https://github.com/r06922019/butt_lion_paper_notes"},{"title":"theburgman21/Pix2Pix-Deblurrer","url":"https://github.com/theburgman21/Pix2Pix-Deblurrer"},{"title":"Paul92/cp_2020","url":"https://github.com/Paul92/cp_2020"},{"title":"AlliBalliBaba/PixFace","url":"https://github.com/AlliBalliBaba/PixFace"},{"title":"bionanoimaging/cellSTORM-Tensorflow","url":"https://github.com/bionanoimaging/cellSTORM-Tensorflow"},{"title":"01pooja10/Sketch-to-Shoe","url":"https://github.com/01pooja10/Sketch-to-Shoe"},{"title":"AbhinavTalari/Night2Day","url":"https://github.com/AbhinavTalari/Night2Day"},{"title":"sdnr1/c-gan_pix2pix","url":"https://github.com/sdnr1/c-gan_pix2pix"},{"title":"AlliBalliBaba/PixFace-Neural-Network","url":"https://github.com/AlliBalliBaba/PixFace-Neural-Network"},{"title":"xiuyu0000/papers_with_examples","url":"https://github.com/xiuyu0000/papers_with_examples/tree/main/pix2pix"},{"title":"code-implementation1/Code6","url":"https://github.com/code-implementation1/Code6/tree/main/Pix2Pix"},{"title":"yoyotv/Image-derain-via-CGAN","url":"https://github.com/yoyotv/Image-derain-via-CGAN"},{"title":"tbullmann/imagetranslation-tensorflow","url":"https://github.com/tbullmann/imagetranslation-tensorflow"},{"title":"AquibPy/Cycle-GAN","url":"https://github.com/AquibPy/Cycle-GAN"},{"title":"RAGHAV2998/Everybody-Can-Dance-Now-Video-game-version-","url":"https://github.com/RAGHAV2998/Everybody-Can-Dance-Now-Video-game-version-"},{"title":"georg-wolflein/hoechstgan","url":"https://github.com/georg-wolflein/hoechstgan"},{"title":"OFRIN/Tensorflow_Pixel2Pixel","url":"https://github.com/OFRIN/Tensorflow_Pixel2Pixel"},{"title":"linxi159/Tips-and-tricks-to-train-GANs","url":"https://github.com/linxi159/Tips-and-tricks-to-train-GANs"},{"title":"fdasilva59/Pix2Pix-Kubeflow-Demo","url":"https://github.com/fdasilva59/Pix2Pix-Kubeflow-Demo"},{"title":"shikhadahiya/Image-to-image-translation-using-C-GAN","url":"https://github.com/shikhadahiya/Image-to-image-translation-using-C-GAN"},{"title":"SeonbeomKim/TensorFlow-pix2pix","url":"https://github.com/SeonbeomKim/TensorFlow-pix2pix"},{"title":"mandalarotation/PixdosepiX-OpenKBP---2020-AAPM-Grand-Challenge-","url":"https://github.com/mandalarotation/PixdosepiX-OpenKBP---2020-AAPM-Grand-Challenge-"},{"title":"laclark/cuneiform_lineart","url":"https://github.com/laclark/cuneiform_lineart"},{"title":"XJhaoren/Academic-Group","url":"https://github.com/XJhaoren/Academic-Group"},{"title":"vamsi3/pix2pix","url":"https://github.com/vamsi3/pix2pix"},{"title":"MS-Mind/MS-Code-06","url":"https://github.com/MS-Mind/MS-Code-06/tree/main/Pix2Pix"},{"title":"ryanwng12/img-colorization","url":"https://github.com/ryanwng12/img-colorization"},{"title":"dwen3232/op-colorization","url":"https://github.com/dwen3232/op-colorization"},{"title":"asyrovprog/cs230project","url":"https://github.com/asyrovprog/cs230project"},{"title":"INOS-soft/Bro-coil","url":"https://github.com/INOS-soft/Bro-coil"},{"title":"komeiharada/learn_DL_together","url":"https://github.com/komeiharada/learn_DL_together"},{"title":"darth-c0d3r/pix2pix","url":"https://github.com/darth-c0d3r/pix2pix"},{"title":"INOS-soft/Python-Tools","url":"https://github.com/INOS-soft/Python-Tools"},{"title":"INOS-soft/AI","url":"https://github.com/INOS-soft/AI"},{"title":"bxck75/piss-ant-pix2pix","url":"https://github.com/bxck75/piss-ant-pix2pix"},{"title":"INOS-soft/KuE.electo-waffle","url":"https://github.com/INOS-soft/KuE.electo-waffle"},{"title":"nishantcoder97/cgandemo","url":"https://github.com/nishantcoder97/cgandemo"},{"title":"MasoumehVahedi/Pix2Pix-GAN-model","url":"https://github.com/MasoumehVahedi/Pix2Pix-GAN-model"},{"title":"YoungWoong-Cho/Decay","url":"https://github.com/YoungWoong-Cho/Decay"},{"title":"Nguyendat-bit/pix2pix-tensorflow","url":"https://github.com/Nguyendat-bit/pix2pix-tensorflow"},{"title":"AsianZeus/Ooze-Handwritten-Text-Generator","url":"https://github.com/AsianZeus/Ooze-Handwritten-Text-Generator"},{"title":"oliverquintana/cGAN","url":"https://github.com/oliverquintana/cGAN"},{"title":"hariv/pix2pix","url":"https://github.com/hariv/pix2pix"},{"title":"Yodai1996/CV","url":"https://github.com/Yodai1996/CV"},{"title":"tiwarikajal/SketchIT--Conversion-of-Images-to-Sketches-using-Conditional-GAN","url":"https://github.com/tiwarikajal/SketchIT--Conversion-of-Images-to-Sketches-using-Conditional-GAN"},{"title":"telecombcn-dl/2018-dlcv-team2","url":"https://github.com/telecombcn-dl/2018-dlcv-team2"},{"title":"GH3927/Pix2Pix-applied-to-cranes","url":"https://github.com/GH3927/Pix2Pix-applied-to-cranes"},{"title":"alililia/ms_extend","url":"https://github.com/alililia/ms_extend/tree/main/gpu_pix2pix"},{"title":"VedantDere0104/Pix2Pix_GAN","url":"https://github.com/VedantDere0104/Pix2Pix_GAN"},{"title":"weipeng0703/Pix2Pix_MindSpore_For_PaperWithCode","url":"https://github.com/weipeng0703/Pix2Pix_MindSpore_For_PaperWithCode/tree/main/Pix2Pix"},{"title":"2023-MindSpore-1/ms-code-6","url":"https://github.com/2023-MindSpore-1/ms-code-6/tree/main/Pix2PixHD"},{"title":"carlosh93/sfr_hb-irit-uis","url":"https://github.com/carlosh93/sfr_hb-irit-uis"},{"title":"saviaga/faceswap","url":"https://github.com/saviaga/faceswap"},{"title":"leemathew1998/RG","url":"https://github.com/leemathew1998/RG"},{"title":"zuobinxiong/pix2pix-tensorflow","url":"https://github.com/zuobinxiong/pix2pix-tensorflow"},{"title":"MarvinLavechin/imagetranslation-tensorflow","url":"https://github.com/MarvinLavechin/imagetranslation-tensorflow"},{"title":"itsuki8914/pix2pix-automaticColorization","url":"https://github.com/itsuki8914/pix2pix-automaticColorization"},{"title":"haratzouvara/image_restoration","url":"https://github.com/haratzouvara/image_restoration"},{"title":"Maxencephilbert/In_Silico_Labeling_CBIO_internship","url":"https://github.com/Maxencephilbert/In_Silico_Labeling_CBIO_internship"},{"title":"miguel-rodrigo/dot-csv-pix2pix","url":"https://github.com/miguel-rodrigo/dot-csv-pix2pix"},{"title":"skabbit/pix2pix-webcam","url":"https://github.com/skabbit/pix2pix-webcam"},{"title":"mohammadAbbasniya/Pix2Pix-from-scratch","url":"https://github.com/mohammadAbbasniya/Pix2Pix-from-scratch"},{"title":"enstan/pix2pix_h5-","url":"https://github.com/enstan/pix2pix_h5-"},{"title":"pooriyasafaei/cityscapes_pix2pix","url":"https://github.com/pooriyasafaei/cityscapes_pix2pix"},{"title":"BH94/cGANs-tensorflow-Python","url":"https://github.com/BH94/cGANs-tensorflow-Python"},{"title":"lukeandshuo/IR2VI_journal","url":"https://github.com/lukeandshuo/IR2VI_journal"},{"title":"tomgillooly/geogan","url":"https://github.com/tomgillooly/geogan"},{"title":"PieterBijl/Group28","url":"https://github.com/PieterBijl/Group28"},{"title":"kulkarnikeerti/Image-to-image-translation-using-cGAN","url":"https://github.com/kulkarnikeerti/Image-to-image-translation-using-cGAN"},{"title":"Beny-Maleki/Pix2PixTorch","url":"https://github.com/Beny-Maleki/Pix2PixTorch"},{"title":"json9512/sonarToimage","url":"https://github.com/json9512/sonarToimage"},{"title":"mastanimahdi/pix2pix","url":"https://github.com/mastanimahdi/pix2pix"},{"title":"sidneykingsley/fyp","url":"https://github.com/sidneykingsley/fyp"},{"title":"amitaydr/Hackaton2018","url":"https://github.com/amitaydr/Hackaton2018"},{"title":"abods/generative_painting","url":"https://github.com/abods/generative_painting"},{"title":"mohmmadweb/Generative-HW3-Q5","url":"https://github.com/mohmmadweb/Generative-HW3-Q5"},{"title":"2023-MindSpore-1/ms-code-215","url":"https://github.com/2023-MindSpore-1/ms-code-215/tree/main/Pix2Pix"},{"title":"aigitsaj13/pix2pix-model","url":"https://github.com/aigitsaj13/pix2pix-model"},{"title":"Nisnab/Pix2Pix","url":"https://github.com/Nisnab/Pix2Pix"},{"title":"Mind23-2/MindCode-61","url":"https://github.com/Mind23-2/MindCode-61"},{"title":"curioserve/pix2pix","url":"https://github.com/curioserve/pix2pix"},{"title":"PDEUXA/AIF_CYCLEGAN","url":"https://github.com/PDEUXA/AIF_CYCLEGAN"},{"title":"raoofzare/Pix2Pix_cityscapes","url":"https://github.com/raoofzare/Pix2Pix_cityscapes"},{"title":"omid-d/Pix2Pix-for-Cityscapes-Dataset","url":"https://github.com/omid-d/Pix2Pix-for-Cityscapes-Dataset"},{"title":"msmrexe/cs-projects","url":"https://github.com/msmrexe/cs-projects/blob/0af76076c0b1166276a5ac5f89b05a8102be8754/uni-masters/generative-models/GM%20Proj%2003%20-%20Pix2Pix.ipynb"},{"title":"vaibhavjindal/pix2pix-pytorch","url":"https://github.com/vaibhavjindal/pix2pix-pytorch"},{"title":"sidneykingsley/pix2pix-tensorflow","url":"https://github.com/sidneykingsley/pix2pix-tensorflow"},{"title":"Vladislav-IS/dls_project_pix2pix","url":"https://github.com/Vladislav-IS/dls_project_pix2pix"},{"title":"sigtot/unet-auto","url":"https://github.com/sigtot/unet-auto"},{"title":"NeuralVFX/pix2pix","url":"https://github.com/NeuralVFX/pix2pix"},{"title":"tbullmann/imagesegmentation-tensorflow","url":"https://github.com/tbullmann/imagesegmentation-tensorflow"},{"title":"epochlab/xres","url":"https://github.com/epochlab/xres"},{"title":"fraxea/pix2pix","url":"https://github.com/fraxea/pix2pix"},{"title":"kingcheng2000/GAN","url":"https://github.com/kingcheng2000/GAN"},{"title":"ranjith0430/ML-tutorials","url":"https://github.com/ranjith0430/ML-tutorials"},{"title":"mohammad-shirkhani/pix2pix","url":"https://github.com/mohammad-shirkhani/pix2pix"},{"title":"mcaseyrehm/pix2pixColab","url":"https://github.com/mcaseyrehm/pix2pixColab"},{"title":"random-quark/pix2pix-tensorflow","url":"https://github.com/random-quark/pix2pix-tensorflow"},{"title":"chez8990/Image2ImageTranslation","url":"https://github.com/chez8990/Image2ImageTranslation"},{"title":"amittiwary42/pix2pix-NNFL","url":"https://github.com/amittiwary42/pix2pix-NNFL"},{"title":"silgena/pix2pix","url":"https://github.com/silgena/pix2pix"},{"title":"GH3927/pix2pix_linemod_duck","url":"https://github.com/GH3927/pix2pix_linemod_duck"},{"title":"pscmap13/pix2pix","url":"https://github.com/pscmap13/pix2pix"},{"title":"DavidCastilloAlvarado/U-NET_AUTOENCODER","url":"https://github.com/DavidCastilloAlvarado/U-NET_AUTOENCODER"},{"title":"sroutray/pix2pix-isola","url":"https://github.com/sroutray/pix2pix-isola"},{"title":"ChandhiniG/Generate-Stylized-Image-from-Edges","url":"https://github.com/ChandhiniG/Generate-Stylized-Image-from-Edges"},{"title":"hero9968/pix2pix-tensorflow","url":"https://github.com/hero9968/pix2pix-tensorflow"},{"title":"alpha-davidson/sun_cgan","url":"https://github.com/alpha-davidson/sun_cgan"},{"title":"ucsd-ml-arts/ml-art-final-chandhini-g-1","url":"https://github.com/ucsd-ml-arts/ml-art-final-chandhini-g-1"},{"title":"leemathew1998/GradientWeight","url":"https://github.com/leemathew1998/GradientWeight"},{"title":"harshitbhushan68/Pix-2-Pix","url":"https://github.com/harshitbhushan68/Pix-2-Pix"},{"title":"g61412333/pix2pix-tensorflow","url":"https://github.com/g61412333/pix2pix-tensorflow"},{"title":"awesomephant/vf-installation","url":"https://github.com/awesomephant/vf-installation"},{"title":"FHomps/ADViSE","url":"https://github.com/FHomps/ADViSE"},{"title":"ArenGolazizian/Pix2Pix-Cityscapes-Seg2Real","url":"https://github.com/ArenGolazizian/Pix2Pix-Cityscapes-Seg2Real"},{"title":"pokurin123/pix2pix_try","url":"https://github.com/pokurin123/pix2pix_try"},{"title":"FrancescoMarchesini/pixToPix","url":"https://github.com/FrancescoMarchesini/pixToPix"},{"title":"JobQiu/hackrice","url":"https://github.com/JobQiu/hackrice"},{"title":"svikramank/pix2pix","url":"https://github.com/svikramank/pix2pix"},{"title":"MindSpore-paper-code-2/code2","url":"https://github.com/MindSpore-paper-code-2/code2/tree/main/Pix2Pix"},{"title":"tianhai123/pix2pix","url":"https://github.com/tianhai123/pix2pix"},{"title":"gerardoglz/GANs","url":"https://github.com/gerardoglz/GANs"},{"title":"jonryf/deep-learning-image-colorization-using-gan","url":"https://github.com/jonryf/deep-learning-image-colorization-using-gan"},{"title":"BrookInternSOMA/pix2pix-barcode","url":"https://github.com/BrookInternSOMA/pix2pix-barcode"},{"title":"PuchatekwSzortach/pix2pix","url":"https://github.com/PuchatekwSzortach/pix2pix"},{"title":"gcwl/pytorch-pix2pix","url":"https://github.com/gcwl/pytorch-pix2pix"},{"title":"Mind23-2/MindCode-5","url":"https://github.com/Mind23-2/MindCode-5/tree/main/Pix2Pix"},{"title":"Rust401/pixel2piexl","url":"https://github.com/Rust401/pixel2piexl"},{"title":"Alighasemzadeh83/Pix2Pix-implementation-from-scratch","url":"https://github.com/Alighasemzadeh83/Pix2Pix-implementation-from-scratch"},{"title":"ivankunyankin/pix2pix","url":"https://github.com/ivankunyankin/pix2pix"},{"title":"utunga/pix2pix-tensorflow","url":"https://github.com/utunga/pix2pix-tensorflow"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on","task":"Open Vocabulary Semantic Segmentation","dataset_variant":"Cityscapes","rows":5,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"FC-CLIP","paper":"/paper/convolutions-die-hard-open-vocabulary-1","metrics":{"mIoU":"56.2"},"code_links":[{"title":"bytedance/fc-clip","url":"https://github.com/bytedance/fc-clip"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-panoptic-segmentation-on","task":"Unsupervised Panoptic Segmentation","dataset_variant":"Cityscapes","rows":5,"metrics":["PQ"],"first_row_in_archive_order":{"model":"CUPS (54 pseudo-classes)","paper":"/paper/scene-centric-unsupervised-panoptic","metrics":{"PQ":"30.6"},"code_links":[{"title":"visinf/cups","url":"https://github.com/visinf/cups"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-prediction-on-cityscapes-128x128","task":"Video Prediction","dataset_variant":"Cityscapes 128x128","rows":5,"metrics":["FVD","SSIM","PSNR","LPIPS","Cond.","Train","Pred"],"first_row_in_archive_order":{"model":"GHVAEs","paper":"/paper/greedy-hierarchical-variational-autoencoders","metrics":{"Cond.":"2","FVD":"418.00 ± 5.0","LPIPS":"0.193 ± 0.014","Pred":"28","SSIM":"0.740±0.4","Train":"10"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/monocular-depth-estimation-on-cityscapes","task":"Monocular Depth Estimation","dataset_variant":"Cityscapes","rows":3,"metrics":["RMSE","RMSE log","Absolute relative error (AbsRel)","Square relative error (SqRel)"],"first_row_in_archive_order":{"model":"SwinMTL","paper":"/paper/swinmtl-a-shared-architecture-for","metrics":{"Absolute relative error (AbsRel)":"0.089","RMSE":"5.481","RMSE log":"0.139","Square relative error (SqRel)":"1.051"},"code_links":[{"title":"pardistaghavi/swinmtl","url":"https://github.com/pardistaghavi/swinmtl"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multi-task-learning-on-cityscapes","task":"Multi-Task Learning","dataset_variant":"Cityscapes test","rows":3,"metrics":["mIoU","RMSE"],"first_row_in_archive_order":{"model":"SwinMTL","paper":"/paper/swinmtl-a-shared-architecture-for","metrics":{"RMSE":"0.51","mIoU":"76.41"},"code_links":[{"title":"pardistaghavi/swinmtl","url":"https://github.com/pardistaghavi/swinmtl"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-18","task":"Semi-Supervised Semantic Segmentation","dataset_variant":"Cityscapes 2% labeled","rows":3,"metrics":["Validation mIoU"],"first_row_in_archive_order":{"model":"GIST and RIST (DeepLabv2 with ResNet101, MSCOCO pre-trained)","paper":"/paper/the-gist-and-rist-of-iterative-self-training","metrics":{"Validation mIoU":"53.51%"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-19","task":"Semi-Supervised Semantic Segmentation","dataset_variant":"Cityscapes 5% labeled","rows":3,"metrics":["Validation mIoU"],"first_row_in_archive_order":{"model":"GIST and RIST (DeepLabv2 with ResNet101, MSCOCO pre-trained)","paper":"/paper/the-gist-and-rist-of-iterative-self-training","metrics":{"Validation mIoU":"59.98%"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-35","task":"Semi-Supervised Semantic Segmentation","dataset_variant":"Cityscapes 93 labeled","rows":3,"metrics":["Validation mIoU"],"first_row_in_archive_order":{"model":"AEL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)","paper":"/paper/semi-supervised-semantic-segmentation-via-2","metrics":{"Validation mIoU":"74.28"},"code_links":[{"title":"hzhupku/semiseg-ael","url":"https://github.com/hzhupku/semiseg-ael"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-prediction-on-cityscapes-1","task":"Video Prediction","dataset_variant":"Cityscapes","rows":3,"metrics":["LPIPS","MS-SSIM"],"first_row_in_archive_order":{"model":"DMVFN","paper":"/paper/a-dynamic-multi-scale-voxel-flow-network-for","metrics":{"LPIPS":"0.0558","MS-SSIM":"0.9573"},"code_links":[{"title":"megvii-research/CVPR2023-DMVFN","url":"https://github.com/megvii-research/CVPR2023-DMVFN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/depth-estimation-on-cityscapes-test","task":"Depth Estimation","dataset_variant":"Cityscapes test","rows":2,"metrics":["RMSE"],"first_row_in_archive_order":{"model":"SwinMTL","paper":"/paper/swinmtl-a-shared-architecture-for","metrics":{"RMSE":"6.352"},"code_links":[{"title":"pardistaghavi/swinmtl","url":"https://github.com/pardistaghavi/swinmtl"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/edge-detection-on-cityscapes","task":"Edge Detection","dataset_variant":"Cityscapes test","rows":2,"metrics":["AP","Maximum F-measure"],"first_row_in_archive_order":{"model":"RPCNet","paper":"/paper/joint-semantic-segmentation-and-boundary","metrics":{"AP":"86.15%","Maximum F-measure":"84.88%"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/real-time-semantic-segmentation-on-cityscapes-3","task":"Real-Time Semantic Segmentation","dataset_variant":"Cityscapes","rows":2,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"S^2-FPN34","paper":"/paper/s-textsuperscript-2-fpn-scale-ware-strip","metrics":{"mIoU":"77.4"},"code_links":[{"title":"mohamedac29/s2-fpn","url":"https://github.com/mohamedac29/s2-fpn"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/robust-object-detection-on-cityscapes","task":"Robust Object Detection","dataset_variant":"Cityscapes test","rows":2,"metrics":["mPC [AP]","rPC [%]"],"first_row_in_archive_order":{"model":"Faster R-CNN with Stylized Training Data","paper":"/paper/benchmarking-robustness-in-object-detection","metrics":{"mPC [AP]":"17.2","rPC [%]":"47.4"},"code_links":[{"title":"bethgelab/imagecorruptions","url":"https://github.com/bethgelab/imagecorruptions"},{"title":"bethgelab/robust-detection-benchmark","url":"https://github.com/bethgelab/robust-detection-benchmark"},{"title":"bethgelab/stylize-datasets","url":"https://github.com/bethgelab/stylize-datasets"},{"title":"bethgelab/mmdetection","url":"https://github.com/bethgelab/mmdetection"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes-2","task":"Semantic Segmentation","dataset_variant":"Cityscapes","rows":2,"metrics":["mIoU","Pixel Accuracy"],"first_row_in_archive_order":{"model":"SPFNet34M","paper":"/paper/s-textsuperscript-2-fpn-scale-ware-strip","metrics":{"mIoU":"77.8"},"code_links":[{"title":"mohamedac29/s2-fpn","url":"https://github.com/mohamedac29/s2-fpn"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-40","task":"Semi-Supervised Semantic Segmentation","dataset_variant":"Cityscapes with extra (no coarse labels)","rows":2,"metrics":["Validation mIoU"],"first_row_in_archive_order":{"model":"Dense FixMatch (DeepLabv3+ ResNet-101, over-sampling, single pass eval)","paper":"/paper/dense-fixmatch-a-simple-semi-supervised","metrics":{"Validation mIoU":"80.82"},"code_links":[{"title":"miquelmarti/DenseFixMatch","url":"https://github.com/miquelmarti/DenseFixMatch"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/2d-semantic-segmentation-on-cityscapes-val","task":"2D Semantic Segmentation","dataset_variant":"Cityscapes val","rows":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"SERNet-Former","paper":"/paper/sernet-former-semantic-segmentation-by","metrics":{"mIoU":"87.35"},"code_links":[{"title":"serdarch/sernet-former","url":"https://github.com/serdarch/sernet-former"},{"title":"serdarch/SERNet-Former","url":"https://github.com/serdarch/SERNet-Former/blob/main/README.md"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-generation-on-cityscapes-25k-256x512","task":"Image Generation","dataset_variant":"Cityscapes-25K 256x512","rows":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"SB-GAN","paper":"/paper/semantic-bottleneck-scene-generation","metrics":{"FID":"62.97"},"code_links":[{"title":"azadis/SB-GAN","url":"https://github.com/azadis/SB-GAN"},{"title":"liorfrenkel1992/SB-GAN","url":"https://github.com/liorfrenkel1992/SB-GAN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-generation-on-cityscapes-5k-256x512","task":"Image Generation","dataset_variant":"Cityscapes-5K 256x512","rows":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"SB-GAN","paper":"/paper/semantic-bottleneck-scene-generation","metrics":{"FID":"65.49"},"code_links":[{"title":"azadis/SB-GAN","url":"https://github.com/azadis/SB-GAN"},{"title":"liorfrenkel1992/SB-GAN","url":"https://github.com/liorfrenkel1992/SB-GAN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/instance-segmentation-on-cityscapes-1","task":"Instance Segmentation","dataset_variant":"Cityscapes","rows":1,"metrics":["AP"],"first_row_in_archive_order":{"model":"CAST","paper":"/paper/cast-contrastive-adaptation-and-distillation","metrics":{"AP":"33.9"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/interactive-segmentation-on-cityscapes-val","task":"Interactive Segmentation","dataset_variant":"Cityscapes val","rows":1,"metrics":["Instance Average IoU"],"first_row_in_archive_order":{"model":"IOG","paper":"/paper/interactive-object-segmentation-with-inside","metrics":{"Instance Average IoU":"83.8"},"code_links":[{"title":"shiyinzhang/Inside-Outside-Guidance","url":"https://github.com/shiyinzhang/Inside-Outside-Guidance"},{"title":"shiyinzhang/Pixel-ImageNet","url":"https://github.com/shiyinzhang/Pixel-ImageNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/knowledge-distillation-on-cityscapes","task":"Knowledge Distillation","dataset_variant":"Cityscapes","rows":1,"metrics":["AP"],"first_row_in_archive_order":{"model":"CAST","paper":"/paper/cast-contrastive-adaptation-and-distillation","metrics":{"AP":"33.9"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/overlapped-10-1-on-cityscapes","task":"Overlapped 10-1","dataset_variant":"Cityscapes","rows":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"MiB+AWT","paper":"/paper/attribution-aware-weight-transfer-a-warm","metrics":{"mIoU":"44.9"},"code_links":[{"title":"dfki-av/awt-for-ciss","url":"https://github.com/dfki-av/awt-for-ciss"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/overlapped-14-1-on-cityscapes","task":"Overlapped 14-1","dataset_variant":"Cityscapes","rows":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"MiB+AWT","paper":"/paper/attribution-aware-weight-transfer-a-warm","metrics":{"mIoU":"46.9"},"code_links":[{"title":"dfki-av/awt-for-ciss","url":"https://github.com/dfki-av/awt-for-ciss"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/real-time-instance-segmentation-on-cityscapes","task":"Real-time Instance Segmentation","dataset_variant":"Cityscapes test","rows":1,"metrics":["AP"],"first_row_in_archive_order":{"model":"CenterPoly","paper":"/paper/centerpoly-real-time-instance-segmentation","metrics":{"AP":"15.54"},"code_links":[{"title":"hu64/centerpoly","url":"https://github.com/hu64/centerpoly"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/scene-parsing-on-cityscapes-test","task":"Scene Parsing","dataset_variant":"Cityscapes test","rows":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"VCD No Coarse","paper":"/paper/variational-context-deformable-convnets-for","metrics":{"mIoU":"82.3"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semi-supervised-instance-segmentation-on","task":"Semi-Supervised Instance Segmentation","dataset_variant":"Cityscapes","rows":1,"metrics":["AP"],"first_row_in_archive_order":{"model":"CAST","paper":"/paper/cast-contrastive-adaptation-and-distillation","metrics":{"AP":"33.9"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-43","task":"Semi-Supervised Semantic Segmentation","dataset_variant":"Cityscapes 10% labeled","rows":1,"metrics":["Mean IoU (class)"],"first_row_in_archive_order":{"model":"IM++ (416x208, 2.7m parameters, no pretraining)","paper":"/paper/inconsistency-masks-removing-the-uncertainty","metrics":{"Mean IoU (class)":"0.428"},"code_links":[{"title":"michaelvorndran/inconsistencymasks","url":"https://github.com/michaelvorndran/inconsistencymasks"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-semantic-segmentation-on-1","task":"Unsupervised Semantic Segmentation","dataset_variant":"Cityscapes val","rows":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"Segmenter ViT-S/16","paper":"/paper/drive-segment-unsupervised-semantic","metrics":{"mIoU":"21.8"},"code_links":[{"title":"vobecant/DriveAndSegment","url":"https://github.com/vobecant/DriveAndSegment"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-16","task":"Weakly-Supervised Semantic Segmentation","dataset_variant":"Cityscapes val","rows":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"CARB","paper":"/paper/weakly-supervised-semantic-segmentation-for-1","metrics":{"mIoU":"52.1"},"code_links":[{"title":"k0u-id/carb","url":"https://github.com/k0u-id/carb"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-17","task":"Weakly-Supervised Semantic Segmentation","dataset_variant":"Cityscapes test","rows":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"CARB","paper":"/paper/weakly-supervised-semantic-segmentation-for-1","metrics":{"mIoU":"51.8"},"code_links":[{"title":"k0u-id/carb","url":"https://github.com/k0u-id/carb"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/boosting-domain-generalized-and-adaptive","title":"Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability","date":"2025-06-26","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/farcluss-fuzzy-adaptive-rebalancing-and","title":"FARCLUSS: Fuzzy Adaptive Rebalancing and Contrastive Uncertainty Learning for Semi-Supervised Semantic Segmentation","date":"2025-06-11","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/cast-contrastive-adaptation-and-distillation","title":"CAST: Contrastive Adaptation and Distillation for Semi-Supervised Instance Segmentation","date":"2025-05-28","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/the-missing-point-in-vision-transformers-for","title":"The Missing Point in Vision Transformers for Universal Image Segmentation","date":"2025-05-26","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/scene-centric-unsupervised-panoptic","title":"Scene-Centric Unsupervised Panoptic Segmentation","date":"2025-04-02","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":0,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/your-vit-is-secretly-an-image-segmentation-1","title":"Your ViT is Secretly an Image Segmentation Model","date":"2025-03-24","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/generalized-diffusion-detector-mining-robust","title":"Generalized Diffusion Detector: Mining Robust Features from Diffusion Models for Domain-Generalized Detection","date":"2025-03-03","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/vpnext-rethinking-dense-decoding-for-plain","title":"VPNeXt -- Rethinking Dense Decoding for Plain Vision Transformer","date":"2025-02-23","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/confidence-weighted-boundary-aware-learning","title":"Confidence-Weighted Boundary-Aware Learning for Semi-Supervised Semantic Segmentation","date":"2025-02-21","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/physaug-a-physical-guided-and-frequency-based","title":"PhysAug: A Physical-guided and Frequency-based Data Augmentation for Single-Domain Generalized Object Detection","date":"2024-12-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/grapix-exploring-graph-modularity","title":"GraPix: Exploring Graph Modularity Optimization for Unsupervised Pixel Clustering","date":"2024-12-04","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/cosmos-cross-modality-self-distillation-for","title":"COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training","date":"2024-12-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/corrclip-reconstructing-correlations-in-clip","title":"CorrCLIP: Reconstructing Correlations in CLIP with Off-the-Shelf Foundation Models for Open-Vocabulary Semantic Segmentation","date":"2024-11-15","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":0,"samples_unverified":9,"pointer_only_for_licence":9,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/harnessing-vision-foundation-models-for-high","title":"Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation","date":"2024-11-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rethinking-decoders-for-transformer-based","title":"Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective","date":"2024-11-05","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/unimatch-v2-pushing-the-limit-of-semi","title":"UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation","date":"2024-10-14","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":2,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/proxyclip-proxy-attention-improves-clip-for","title":"ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation","date":"2024-08-09","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":3,"samples_unverified":6,"pointer_only_for_licence":9,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/csfnet-a-cosine-similarity-fusion-network-for","title":"CSFNet: A Cosine Similarity Fusion Network for Real-Time RGB-X Semantic Segmentation of Driving Scenes","date":"2024-07-01","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/dsnet-a-novel-way-to-use-atrous-convolutions","title":"DSNet: A Novel Way to Use Atrous Convolutions in Semantic Segmentation","date":"2024-06-06","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/revisiting-and-maximizing-temporal-knowledge","title":"Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation","date":"2024-05-31","rows_on_this_dataset":8,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":6,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/boosting-unsupervised-semantic-segmentation","title":"Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals","date":"2024-04-25","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/ttd-text-tag-self-distillation-enhancing","title":"TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias","date":"2024-03-30","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/swinmtl-a-shared-architecture-for","title":"SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images","date":"2024-03-15","rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/eagle-eigen-aggregation-learning-for-object","title":"EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation","date":"2024-03-03","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":19,"samples_ran":14,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/sernet-former-semantic-segmentation-by","title":"SERNet-Former: Semantic Segmentation by Efficient Residual Network with Attention-Boosting Gates and Attention-Fusion Networks","date":"2024-01-28","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/inconsistency-masks-removing-the-uncertainty","title":"Inconsistency Masks: Removing the Uncertainty from Input-Pseudo-Label Pairs","date":"2024-01-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/depth-anything-unleashing-the-power-of-large","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","date":"2024-01-19","rows_on_this_dataset":2,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":3,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fully-attentional-networks-with-self-emerging-1","title":"Fully Attentional Networks with Self-emerging Token Labeling","date":"2024-01-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unsupervised-universal-image-segmentation","title":"Unsupervised Universal Image Segmentation","date":"2023-12-28","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":13,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mgdepth-motion-guided-cost-volume-for-self","title":"Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic Scenes","date":"2023-12-23","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":0,"samples_unverified":9,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/harnessing-diffusion-models-for-visual","title":"Harnessing Diffusion Models for Visual Perception with Meta Prompts","date":"2023-12-22","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":4,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/weakly-supervised-semantic-segmentation-for-1","title":"Weakly Supervised Semantic Segmentation for Driving Scenes","date":"2023-12-21","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/tagalign-improving-vision-language-alignment","title":"TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification","date":"2023-12-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unlocking-pre-trained-image-backbones-for","title":"Unlocking Pre-trained Image Backbones for Semantic Image Synthesis","date":"2023-12-20","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/object-aware-domain-generalization-for-object","title":"Object-Aware Domain Generalization for Object Detection","date":"2023-12-19","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/expand-and-quantize-unsupervised-semantic","title":"Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization","date":"2023-12-12","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/vltseg-simple-transfer-of-clip-based-vision","title":"Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learning","date":"2023-12-04","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mrfp-learning-generalizable-semantic","title":"MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation","date":"2023-11-30","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/semivl-semi-supervised-semantic-segmentation","title":"SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance","date":"2023-11-27","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/mobile-seed-joint-semantic-segmentation-and","title":"Mobile-Seed: Joint Semantic Segmentation and Boundary Detection for Mobile Robots","date":"2023-11-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/switching-temporary-teachers-for-semi","title":"Switching Temporary Teachers for Semi-Supervised Semantic Segmentation","date":"2023-09-21","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/spatially-guiding-unsupervised-semantic","title":"Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling","date":"2023-09-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/semi-supervised-semantic-segmentation-via-3","title":"Semi-Supervised Semantic Segmentation via Marginal Contextual Information","date":"2023-08-26","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/diffuse-attend-and-segment-unsupervised-zero","title":"Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion","date":"2023-08-23","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/convolutions-die-hard-open-vocabulary-1","title":"Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP","date":"2023-08-04","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/resolution-aware-design-of-atrous-rates-for","title":"Resolution-Aware Design of Atrous Rates for Semantic Segmentation Networks","date":"2023-07-26","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/conditional-boundary-loss-for-semantic","title":"Conditional Boundary Loss for Semantic Segmentation","date":"2023-07-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hyperbolic-active-learning-for-semantic","title":"Hyperbolic Active Learning for Semantic Segmentation under Domain Shift","date":"2023-06-19","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":3,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/corrmatch-label-propagation-via-correlation","title":"CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation","date":"2023-06-07","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/wavelet-based-unsupervised-label-to-image-1","title":"Wavelet-based Unsupervised Label-to-Image Translation","date":"2023-05-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/autofocusformer-image-segmentation-off-the","title":"AutoFocusFormer: Image Segmentation off the Grid","date":"2023-04-24","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/intra-batch-supervision-for-panoptic-1","title":"Intra-Batch Supervision for Panoptic Segmentation on High-Resolution Images","date":"2023-04-17","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/clip-surgery-for-better-explainability-with","title":"A Closer Look at the Explainability of Contrastive Language-Image Pre-training","date":"2023-04-12","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/ddp-diffusion-model-for-dense-visual","title":"DDP: Diffusion Model for Dense Visual Prediction","date":"2023-03-30","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/leveraging-hidden-positives-for-unsupervised","title":"Leveraging Hidden Positives for Unsupervised Semantic Segmentation","date":"2023-03-27","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-dynamic-multi-scale-voxel-flow-network-for","title":"A Dynamic Multi-Scale Voxel Flow Network for Video Prediction","date":"2023-03-17","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-simple-framework-for-open-vocabulary","title":"A Simple Framework for Open-Vocabulary Segmentation and Detection","date":"2023-03-14","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/soft-labelling-for-semantic-segmentation","title":"Soft labelling for semantic segmentation: Bringing coherence to label down-sampling","date":"2023-02-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/recurrent-contour-based-instance-segmentation","title":"Recurrent Generic Contour-based Instance Segmentation with Progressive Learning","date":"2023-01-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-to-generate-text-grounded-mask-for","title":"Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs","date":"2022-12-01","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":1,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/conservative-progressive-collaborative","title":"Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation","date":"2022-11-30","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/oneformer-one-transformer-to-rule-universal","title":"OneFormer: One Transformer to Rule Universal Image Segmentation","date":"2022-11-10","rows_on_this_dataset":12,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/internimage-exploring-large-scale-vision","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","date":"2022-11-10","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":2,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/perceptual-grouping-in-vision-language-models","title":"Perceptual Grouping in Contrastive Vision-Language Models","date":"2022-10-18","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/dense-fixmatch-a-simple-semi-supervised","title":"Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks","date":"2022-10-18","rows_on_this_dataset":8,"code_links":1,"syntology":null},{"paper":"/paper/wavemix-lite-a-resource-efficient-neural-1","title":"WaveMix-Lite: A Resource-efficient Neural Network for Image Analysis","date":"2022-10-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rtformer-efficient-design-for-real-time","title":"RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer","date":"2022-10-13","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/attribution-aware-weight-transfer-a-warm","title":"Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation","date":"2022-10-13","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":1,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/semi-supervised-semantic-segmentation-with-6","title":"Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization","date":"2022-10-10","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/sequential-ensembling-for-semantic","title":"Sequential Ensembling for Semantic Segmentation","date":"2022-10-08","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/dual-pyramid-generative-adversarial-networks","title":"Dual Pyramid Generative Adversarial Networks for Semantic Image Synthesis","date":"2022-10-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dilated-neighborhood-attention-transformer","title":"Dilated Neighborhood Attention Transformer","date":"2022-09-29","rows_on_this_dataset":3,"code_links":7,"syntology":null},{"paper":"/paper/segnext-rethinking-convolutional-attention","title":"SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation","date":"2022-09-18","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/revisiting-weak-to-strong-consistency-in-semi","title":"Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation","date":"2022-08-21","rows_on_this_dataset":5,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":4,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/k-means-mask-transformer","title":"kMaX-DeepLab: k-means Mask Transformer","date":"2022-07-08","rows_on_this_dataset":3,"code_links":3,"syntology":null},{"paper":"/paper/lasermix-for-semi-supervised-lidar-semantic","title":"LaserMix for Semi-Supervised LiDAR Semantic Segmentation","date":"2022-06-30","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/cmt-deeplab-clustering-mask-transformers-for-1","title":"CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation","date":"2022-06-17","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":0,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/s-textsuperscript-2-fpn-scale-ware-strip","title":"S$^2$-FPN: Scale-ware Strip Attention Guided Feature Pyramid Network for Real-time Semantic Segmentation","date":"2022-06-15","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/reco-retrieve-and-co-segment-for-zero-shot-1","title":"ReCo: Retrieve and Co-segment for Zero-shot Transfer","date":"2022-06-14","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/pidnet-a-real-time-semantic-segmentation","title":"PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers","date":"2022-06-04","rows_on_this_dataset":6,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":19,"samples_ran":1,"samples_unverified":18,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/efficientvit-enhanced-linear-attention-for","title":"EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction","date":"2022-05-29","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/wavemix-lite-a-resource-efficient-neural","title":"WaveMix: A Resource-efficient Neural Network for Image Analysis","date":"2022-05-28","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/vision-transformer-adapter-for-dense","title":"Vision Transformer Adapter for Dense Predictions","date":"2022-05-17","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/streaming-multiscale-deep-equilibrium-models","title":"Representation Recycling for Streaming Video Analysis","date":"2022-04-28","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/understanding-the-robustness-in-vision","title":"Understanding The Robustness in Vision Transformers","date":"2022-04-26","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/pp-liteseg-a-superior-real-time-semantic","title":"PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model","date":"2022-04-06","rows_on_this_dataset":8,"code_links":3,"syntology":null},{"paper":"/paper/semi-supervised-semantic-segmentation-with-5","title":"Semi-supervised Semantic Segmentation with Error Localization Network","date":"2022-04-05","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":1,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/improving-generalization-in-federated","title":"Improving Generalization in Federated Learning by Seeking Flat Minima","date":"2022-03-22","rows_on_this_dataset":9,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/drive-segment-unsupervised-semantic","title":"Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation","date":"2022-03-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/delta-distillation-for-efficient-video","title":"Delta Distillation for Efficient Video Processing","date":"2022-03-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unsupervised-semantic-segmentation-by-2","title":"Unsupervised Semantic Segmentation by Distilling Feature Correspondences","date":"2022-03-16","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":8,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/cmx-cross-modal-fusion-for-rgb-x-semantic","title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","date":"2022-03-09","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/semi-supervised-semantic-segmentation-using-2","title":"Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels","date":"2022-03-08","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bending-reality-distortion-aware-transformers","title":"Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation","date":"2022-03-02","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/multi-task-learning-as-a-bargaining-game","title":"Multi-Task Learning as a Bargaining Game","date":"2022-02-02","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pushing-the-limits-of-self-supervised-resnets","title":"Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?","date":"2022-01-13","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":0,"samples_unverified":14,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/2112-14757","title":"A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model","date":"2021-12-29","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/semask-semantically-masked-transformers-for-1","title":"SeMask: Semantically Masked Transformers for Semantic Segmentation","date":"2021-12-23","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/repmlpnet-hierarchical-vision-mlp-with-re","title":"RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality","date":"2021-12-21","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/n-cps-generalising-cross-pseudo-supervision","title":"n-CPS: Generalising Cross Pseudo Supervision to n Networks for Semi-Supervised Semantic Segmentation","date":"2021-12-14","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/masked-attention-mask-transformer-for","title":"Masked-attention Mask Transformer for Universal Image Segmentation","date":"2021-12-02","rows_on_this_dataset":8,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":2,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/denseclip-extract-free-dense-labels-from-clip","title":"Extract Free Dense Labels from CLIP","date":"2021-12-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/semantic-aware-generation-for-self-supervised","title":"Semantic-Aware Generation for Self-Supervised Visual Representation Learning","date":"2021-11-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/perturbed-and-strict-mean-teachers-for-semi","title":"Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation","date":"2021-11-25","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/vice-self-supervised-visual-concept","title":"ViCE: Improving Dense Representation Learning by Superpixelization and Contrasting Cluster Assignment","date":"2021-11-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rethink-dilated-convolution-for-real-time","title":"Rethinking Dilated Convolution for Real-time Semantic Segmentation","date":"2021-11-18","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/hs3-learning-with-proper-task-complexity-in","title":"HS3: Learning with Proper Task Complexity in Hierarchically Supervised Semantic Segmentation","date":"2021-11-03","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/projected-gans-converge-faster","title":"Projected GANs Converge Faster","date":"2021-11-01","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":49,"samples_ran":38,"samples_unverified":11,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hrvit-multi-scale-high-resolution-vision","title":"Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation","date":"2021-11-01","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/regularized-frank-wolfe-for-dense-crfs","title":"Regularized Frank-Wolfe for Dense CRFs: Generalizing Mean Field and Beyond","date":"2021-10-27","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/semi-supervised-semantic-segmentation-via-2","title":"Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning","date":"2021-10-11","rows_on_this_dataset":5,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/usis-unsupervised-semantic-image-synthesis","title":"USIS: Unsupervised Semantic Image Synthesis","date":"2021-09-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/trans4trans-efficient-transformer-for-1","title":"Trans4Trans: Efficient Transformer for Transparent Object and Semantic Scene Segmentation in Real-World Navigation Assistance","date":"2021-08-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/centerpoly-real-time-instance-segmentation","title":"CenterPoly: real-time instance segmentation using bounding polygons","date":"2021-08-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/eeea-net-an-early-exit-evolutionary-neural","title":"EEEA-Net: An Early Exit Evolutionary Neural Architecture Search","date":"2021-08-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/slamp-stochastic-latent-appearance-and-motion","title":"SLAMP: Stochastic Latent Appearance and Motion Prediction","date":"2021-08-05","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/standardized-max-logits-a-simple-yet","title":"Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation","date":"2021-07-23","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/polarized-self-attention-towards-high-quality-1","title":"Polarized Self-Attention: Towards High-quality Pixel-wise Regression","date":"2021-07-02","rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/guidedmix-net-learning-to-improve-pseudo","title":"GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference","date":"2021-06-29","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/volo-vision-outlooker-for-visual-recognition","title":"VOLO: Vision Outlooker for Visual Recognition","date":"2021-06-24","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":1,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/combinatorial-optimization-for-panoptic","title":"Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach","date":"2021-06-06","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/semi-supervised-semantic-segmentation-with-3","title":"Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision","date":"2021-06-02","rows_on_this_dataset":4,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":39,"samples_ran":22,"samples_unverified":17,"pointer_only_for_licence":28,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/segformer-simple-and-efficient-design-for","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","date":"2021-05-31","rows_on_this_dataset":3,"code_links":28,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":86,"samples_ran":48,"samples_unverified":38,"pointer_only_for_licence":15,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/aerial-pass-panoramic-annular-scene","title":"Aerial-PASS: Panoramic Annular Scene Segmentation in Drone Videos","date":"2021-05-15","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/beyond-self-attention-external-attention","title":"Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks","date":"2021-05-05","rows_on_this_dataset":1,"code_links":7,"syntology":null},{"paper":"/paper/semi-supervised-semantic-segmentation-with-2","title":"Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank","date":"2021-04-27","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rethinking-bisenet-for-real-time-semantic","title":"Rethinking BiSeNet For Real-time Semantic Segmentation","date":"2021-04-27","rows_on_this_dataset":6,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":16,"samples_ran":8,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/improve-vision-transformers-training-by","title":"Vision Transformers with Patch Diversification","date":"2021-04-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-simple-baseline-for-semi-supervised","title":"A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation","date":"2021-04-15","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/bootstrapping-semantic-segmentation-with","title":"Bootstrapping Semantic Segmentation with Regional Contrast","date":"2021-04-09","rows_on_this_dataset":7,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":3,"samples_unverified":3,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/inverseform-a-loss-function-for-structured","title":"InverseForm: A Loss Function for Structured Boundary-Aware Segmentation","date":"2021-04-06","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/the-gist-and-rist-of-iterative-self-training","title":"The GIST and RIST of Iterative Self-Training for Semi-Supervised Segmentation","date":"2021-03-31","rows_on_this_dataset":5,"code_links":0,"syntology":null},{"paper":"/paper/picie-unsupervised-semantic-segmentation","title":"PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering","date":"2021-03-30","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":2,"samples_unverified":2,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dilated-spinenet-for-semantic-segmentation","title":"Dilated SpineNet for Semantic Segmentation","date":"2021-03-23","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/efficient-visual-pretraining-with-contrastive","title":"Efficient Visual Pretraining with Contrastive Detection","date":"2021-03-19","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/track-to-detect-and-segment-an-online-multi","title":"Track to Detect and Segment: An Online Multi-Object Tracker","date":"2021-03-16","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/diverse-semantic-image-synthesis-via","title":"Diverse Semantic Image Synthesis via Probability Distribution Modeling","date":"2021-03-11","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":3,"samples_unverified":2,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pixel-wise-anomaly-detection-in-complex","title":"Pixel-wise Anomaly Detection in Complex Driving Scenes","date":"2021-03-09","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/greedy-hierarchical-variational-autoencoders","title":"Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction","date":"2021-03-06","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/generative-adversarial-transformers","title":"Generative Adversarial Transformers","date":"2021-03-01","rows_on_this_dataset":5,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":5,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/temporal-memory-attention-for-video-semantic","title":"Temporal Memory Attention for Video Semantic Segmentation","date":"2021-02-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-monocular-depth-in-dynamic-scenes","title":"Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency","date":"2021-02-04","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":4,"samples_unverified":4,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ikshana-a-theory-of-human-scene-understanding","title":"The Ikshana Hypothesis of Human Scene Understanding","date":"2021-01-21","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/caa-channelized-axial-attention-for-semantic","title":"Channelized Axial Attention for Semantic Segmentation -- Considering Channel Relation within Spatial Attention for Semantic Segmentation","date":"2021-01-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/deep-dual-resolution-networks-for-real-time","title":"Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes","date":"2021-01-15","rows_on_this_dataset":4,"code_links":8,"syntology":null},{"paper":"/paper/repvgg-making-vgg-style-convnets-great-again","title":"RepVGG: Making VGG-style ConvNets Great Again","date":"2021-01-11","rows_on_this_dataset":1,"code_links":25,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":16,"samples_ran":13,"samples_unverified":3,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rethinking-semantic-segmentation-from-a","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","date":"2020-12-31","rows_on_this_dataset":2,"code_links":5,"syntology":null},{"paper":"/paper/focal-frequency-loss-for-generative-models","title":"Focal Frequency Loss for Image Reconstruction and Synthesis","date":"2020-12-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hyperseg-patch-wise-hypernetwork-for-real","title":"HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation","date":"2020-12-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/three-ways-to-improve-semantic-segmentation","title":"Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation","date":"2020-12-19","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/you-only-need-adversarial-supervision-for-1","title":"You Only Need Adversarial Supervision for Semantic Image Synthesis","date":"2020-12-08","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":1,"samples_unverified":6,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fully-convolutional-networks-for-panoptic","title":"Fully Convolutional Networks for Panoptic Segmentation","date":"2020-12-01","rows_on_this_dataset":3,"code_links":6,"syntology":null},{"paper":"/paper/improving-augmentation-and-evaluation-schemes","title":"Improving Augmentation and Evaluation Schemes for Semantic Image Synthesis","date":"2020-11-25","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/segblocks-block-based-dynamic-resolution","title":"SegBlocks: Block-Based Dynamic Resolution Networks for Real-Time Segmentation","date":"2020-11-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/scaling-wide-residual-networks-for-panoptic","title":"Scaling Wide Residual Networks for Panoptic Segmentation","date":"2020-11-23","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/densely-connected-multidilated-convolutional","title":"Densely connected multidilated convolutional networks for dense prediction tasks","date":"2020-11-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-receptive-field-network-for-semantic","title":"Multi Receptive Field Network for Semantic Segmentation","date":"2020-11-17","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/efficient-rgb-d-semantic-segmentation-for","title":"Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis","date":"2020-11-13","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/scene-segmentation-with-dual-relation-aware","title":"Scene Segmentation with Dual Relation-aware Attention Network","date":"2020-08-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/classmix-segmentation-based-data-augmentation","title":"ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning","date":"2020-07-15","rows_on_this_dataset":6,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":19,"samples_ran":5,"samples_unverified":14,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/semantic-segmentation-with-multi-scale","title":"Semantic Segmentation With Multi Scale Spatial Attention For Self Driving Cars","date":"2020-06-30","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multiscale-deep-equilibrium-models","title":"Multiscale Deep Equilibrium Models","date":"2020-06-15","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":10,"samples_unverified":4,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/geometry-aware-instance-segmentation-with","title":"Geometry-Aware Instance Segmentation with Disparity Maps","date":"2020-06-14","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/disentangled-non-local-neural-networks","title":"Disentangled Non-Local Neural Networks","date":"2020-06-11","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/variational-context-deformable-convnets-for","title":"Variational Context-Deformable ConvNets for Indoor Scene Parsing","date":"2020-06-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/sdc-depth-semantic-divide-and-conquer-network","title":"SDC-Depth: Semantic Divide-and-Conquer Network for Monocular Depth Estimation","date":"2020-06-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/interactive-object-segmentation-with-inside","title":"Interactive Object Segmentation With Inside-Outside Guidance","date":"2020-06-01","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/hierarchical-multi-scale-attention-for","title":"Hierarchical Multi-Scale Attention for Semantic Segmentation","date":"2020-05-21","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":1,"samples_unverified":8,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/resnest-split-attention-networks","title":"ResNeSt: Split-Attention Networks","date":"2020-04-19","rows_on_this_dataset":2,"code_links":36,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":48,"samples_ran":8,"samples_unverified":40,"pointer_only_for_licence":23,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/semi-supervised-semantic-segmentation-via","title":"DMT: Dynamic Mutual Training for Semi-Supervised Learning","date":"2020-04-18","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/joint-semantic-segmentation-and-boundary","title":"Joint Semantic Segmentation and Boundary Detection using Iterative Pyramid Contexts","date":"2020-04-16","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/sesame-semantic-editing-of-scenes-by-adding","title":"SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects","date":"2020-04-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/efficientps-efficient-panoptic-segmentation","title":"EfficientPS: Efficient Panoptic Segmentation","date":"2020-04-05","rows_on_this_dataset":6,"code_links":2,"syntology":null},{"paper":"/paper/bisenet-v2-bilateral-network-with-guided","title":"BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation","date":"2020-04-05","rows_on_this_dataset":4,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":6,"samples_unverified":4,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/temporally-distributed-networks-for-fast","title":"Temporally Distributed Networks for Fast Video Semantic Segmentation","date":"2020-04-03","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":2,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/context-prior-for-scene-segmentation","title":"Context Prior for Scene Segmentation","date":"2020-04-03","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/future-video-synthesis-with-object-motion","title":"Future Video Synthesis with Object Motion Prediction","date":"2020-04-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/2003-13328","title":"Strip Pooling: Rethinking Spatial Pooling for Scene Parsing","date":"2020-03-30","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":2,"samples_unverified":9,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dcnas-densely-connected-neural-architecture","title":"DCNAS: Densely Connected Neural Architecture Search for Semantic Image Segmentation","date":"2020-03-26","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/axial-deeplab-stand-alone-axial-attention-for","title":"Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation","date":"2020-03-17","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":3,"samples_unverified":8,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/cars-cant-fly-up-in-the-sky-improving-urban","title":"Cars Can't Fly up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networks","date":"2020-03-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/semantic-flow-for-fast-and-accurate-scene","title":"Semantic Flow for Fast and Accurate Scene Parsing","date":"2020-02-24","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":1,"samples_unverified":7,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/real-time-fusion-network-for-rgb-d-semantic","title":"Real-time Fusion Network for RGB-D Semantic Segmentation Incorporating Unexpected Obstacle Detection for Road-driving Images","date":"2020-02-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/stochastic-latent-residual-video-prediction-1","title":"Stochastic Latent Residual Video Prediction","date":"2020-02-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":2,"samples_unverified":10,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fasterseg-searching-for-faster-real-time-1","title":"FasterSeg: Searching for Faster Real-time Semantic Segmentation","date":"2019-12-23","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":2,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pointrend-image-segmentation-as-rendering","title":"PointRend: Image Segmentation as Rendering","date":"2019-12-17","rows_on_this_dataset":2,"code_links":14,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":18,"samples_ran":5,"samples_unverified":13,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/liteseg-a-novel-lightweight-convnet-for","title":"LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation","date":"2019-12-13","rows_on_this_dataset":6,"code_links":2,"syntology":null},{"paper":"/paper/waterfall-atrous-spatial-pooling-architecture","title":"Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation","date":"2019-12-06","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/polytransform-deep-polygon-transformer-for","title":"PolyTransform: Deep Polygon Transformer for Instance Segmentation","date":"2019-12-05","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/augmix-a-simple-data-processing-method-to","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","date":"2019-12-05","rows_on_this_dataset":1,"code_links":15,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":51,"samples_ran":43,"samples_unverified":8,"pointer_only_for_licence":25,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/semantic-bottleneck-scene-generation","title":"Semantic Bottleneck Scene Generation","date":"2019-11-26","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/panoptic-deeplab-a-simple-strong-and-fast","title":"Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation","date":"2019-11-22","rows_on_this_dataset":6,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":3,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/sinet-extreme-lightweight-portrait","title":"SINet: Extreme Lightweight Portrait Segmentation Networks with Spatial Squeeze Modules and Information Blocking Decoder","date":"2019-11-20","rows_on_this_dataset":1,"code_links":8,"syntology":null},{"paper":"/paper/sognet-scene-overlap-graph-network-for","title":"SOGNet: Scene Overlap Graph Network for Panoptic Segmentation","date":"2019-11-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-to-predict-layout-to-image","title":"Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis","date":"2019-10-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/object-contextual-representations-for","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","date":"2019-09-24","rows_on_this_dataset":7,"code_links":11,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":4,"samples_unverified":5,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ds-pass-detail-sensitive-panoramic-annular","title":"DS-PASS: Detail-Sensitive Panoramic Annular Semantic Segmentation through SwaftNet for Surrounding Sensing","date":"2019-09-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/adaptis-adaptive-instance-selection-network","title":"AdaptIS: Adaptive Instance Selection Network","date":"2019-09-17","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/global-aggregation-then-local-distribution-in","title":"Global Aggregation then Local Distribution in Fully Convolutional Networks","date":"2019-09-16","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":2,"samples_unverified":2,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dual-graph-convolutional-network-for-semantic","title":"Dual Graph Convolutional Network for Semantic Segmentation","date":"2019-09-13","rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/semantic-correlation-promoted-shape-variant-1","title":"Semantic Correlation Promoted Shape-Variant Context for Segmentation","date":"2019-09-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hardnet-a-low-memory-traffic-network","title":"HarDNet: A Low Memory Traffic Network","date":"2019-09-03","rows_on_this_dataset":1,"code_links":24,"syntology":null},{"paper":"/paper/boundary-aware-feature-propagation-for-scene","title":"Boundary-Aware Feature Propagation for Scene Segmentation","date":"2019-08-31","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":1,"samples_unverified":10,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/asymmetric-non-local-neural-networks-for","title":"Asymmetric Non-local Neural Networks for Semantic Segmentation","date":"2019-08-21","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/190807919","title":"Deep High-Resolution Representation Learning for Visual Recognition","date":"2019-08-20","rows_on_this_dataset":3,"code_links":42,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":34,"samples_ran":3,"samples_unverified":31,"pointer_only_for_licence":16,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/semi-supervised-semantic-segmentation-with","title":"Semi-Supervised Semantic Segmentation with High- and Low-level Consistency","date":"2019-08-15","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/squeezenas-fast-neural-architecture-search","title":"SqueezeNAS: Fast neural architecture search for faster semantic segmentation","date":"2019-08-05","rows_on_this_dataset":5,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/exploring-semantic-segmentation-on-the-dct","title":"Exploring Semantic Segmentation on the DCT Representation","date":"2019-07-23","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/benchmarking-robustness-in-object-detection","title":"Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming","date":"2019-07-17","rows_on_this_dataset":3,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":2,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/gated-scnn-gated-shape-cnns-for-semantic","title":"Gated-SCNN: Gated Shape CNNs for Semantic Segmentation","date":"2019-07-12","rows_on_this_dataset":3,"code_links":4,"syntology":null},{"paper":"/paper/learning-data-augmentation-strategies-for","title":"Learning Data Augmentation Strategies for Object Detection","date":"2019-06-26","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/instance-segmentation-by-jointly-optimizing-1","title":"Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth","date":"2019-06-26","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/esnet-an-efficient-symmetric-network-for-real","title":"ESNet: An Efficient Symmetric Network for Real-time Semantic Segmentation","date":"2019-06-24","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/dicenet-dimension-wise-convolutions-for","title":"DiCENet: Dimension-wise Convolutions for Efficient Networks","date":"2019-06-08","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/consistency-regularization-and-cutmix-for","title":"Semi-supervised semantic segmentation needs strong, varied perturbations","date":"2019-06-05","rows_on_this_dataset":3,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/lednet-a-lightweight-encoder-decoder-network","title":"LEDNet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation","date":"2019-05-07","rows_on_this_dataset":2,"code_links":6,"syntology":null},{"paper":"/paper/searching-for-mobilenetv3","title":"Searching for MobileNetV3","date":"2019-05-06","rows_on_this_dataset":1,"code_links":67,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":105,"samples_ran":58,"samples_unverified":47,"pointer_only_for_licence":46,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/improved-conditional-vrnns-for-video","title":"Improved Conditional VRNNs for Video Prediction","date":"2019-04-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/high-resolution-representations-for-labeling","title":"High-Resolution Representations for Labeling Pixels and Regions","date":"2019-04-09","rows_on_this_dataset":1,"code_links":39,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":18,"samples_ran":3,"samples_unverified":15,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/template-based-automatic-search-of-compact","title":"Template-Based Automatic Search of Compact Semantic Segmentation Architectures","date":"2019-04-04","rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/gff-gated-fully-fusion-for-semantic","title":"GFF: Gated Fully Fusion for Semantic Segmentation","date":"2019-04-03","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/dfanet-deep-feature-aggregation-for-real-time","title":"DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation","date":"2019-04-03","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/in-defense-of-pre-trained-imagenet","title":"In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images","date":"2019-03-20","rows_on_this_dataset":2,"code_links":6,"syntology":null},{"paper":"/paper/semantic-image-synthesis-with-spatially","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","date":"2019-03-18","rows_on_this_dataset":1,"code_links":24,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":5,"samples_unverified":4,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deeperlab-single-shot-image-parser","title":"DeeperLab: Single-Shot Image Parser","date":"2019-02-13","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/fast-scnn-fast-semantic-segmentation-network","title":"Fast-SCNN: Fast Semantic Segmentation Network","date":"2019-02-12","rows_on_this_dataset":2,"code_links":24,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":32,"samples_ran":0,"samples_unverified":32,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/upsnet-a-unified-panoptic-segmentation","title":"UPSNet: A Unified Panoptic Segmentation Network","date":"2019-01-12","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/auto-deeplab-hierarchical-neural-architecture","title":"Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation","date":"2019-01-10","rows_on_this_dataset":2,"code_links":12,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/panoptic-feature-pyramid-networks","title":"Panoptic Feature Pyramid Networks","date":"2019-01-08","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":7,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/attention-guided-unified-network-for-panoptic","title":"Attention-guided Unified Network for Panoptic Segmentation","date":"2018-12-10","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-to-fuse-things-and-stuff","title":"Learning to Fuse Things and Stuff","date":"2018-12-04","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/espnetv2-a-light-weight-power-efficient-and","title":"ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network","date":"2018-11-28","rows_on_this_dataset":1,"code_links":10,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":2,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ccnet-criss-cross-attention-for-semantic","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","date":"2018-11-28","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":9,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/multi-path-segmentation-network","title":"ShelfNet for Fast Semantic Segmentation","date":"2018-11-27","rows_on_this_dataset":2,"code_links":6,"syntology":null},{"paper":"/paper/multi-task-learning-as-multi-objective","title":"Multi-Task Learning as Multi-Objective Optimization","date":"2018-10-10","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":19,"samples_ran":2,"samples_unverified":17,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/incorporating-luminance-depth-and-color","title":"Incorporating Luminance, Depth and Color Information by a Fusion-based Network for Semantic Segmentation","date":"2018-09-24","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/efficient-dense-modules-of-asymmetric","title":"Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation","date":"2018-09-17","rows_on_this_dataset":2,"code_links":4,"syntology":null},{"paper":"/paper/searching-for-efficient-multi-scale","title":"Searching for Efficient Multi-Scale Architectures for Dense Image Prediction","date":"2018-09-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dual-attention-network-for-scene-segmentation","title":"Dual Attention Network for Scene Segmentation","date":"2018-09-09","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":0,"samples_unverified":7,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ocnet-object-context-network-for-scene","title":"OCNet: Object Context Network for Scene Parsing","date":"2018-09-04","rows_on_this_dataset":1,"code_links":8,"syntology":null},{"paper":"/paper/psanet-point-wise-spatial-attention-network","title":"PSANet: Point-wise Spatial Attention Network for Scene Parsing","date":"2018-09-01","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/self-supervised-model-adaptation-for","title":"Self-Supervised Model Adaptation for Multimodal Semantic Segmentation","date":"2018-08-11","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/weakly-and-semi-supervised-panoptic","title":"Weakly- and Semi-Supervised Panoptic Segmentation","date":"2018-08-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/bisenet-bilateral-segmentation-network-for","title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","date":"2018-08-02","rows_on_this_dataset":4,"code_links":21,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":18,"samples_ran":6,"samples_unverified":12,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/unet-a-nested-u-net-architecture-for-medical","title":"UNet++: A Nested U-Net Architecture for Medical Image Segmentation","date":"2018-07-18","rows_on_this_dataset":1,"code_links":34,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":28,"samples_ran":5,"samples_unverified":23,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deep-clustering-for-unsupervised-learning-of","title":"Deep Clustering for Unsupervised Learning of Visual Features","date":"2018-07-15","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":5,"samples_unverified":2,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/denseaspp-for-semantic-segmentation-in-street","title":"DenseASPP for Semantic Segmentation in Street Scenes","date":"2018-06-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/contextnet-exploring-context-and-detail-for","title":"ContextNet: Exploring Context and Detail for Semantic Segmentation in Real-time","date":"2018-05-11","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/semi-parametric-image-synthesis","title":"Semi-parametric Image Synthesis","date":"2018-04-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-a-discriminative-feature-network-for","title":"Learning a Discriminative Feature Network for Semantic Segmentation","date":"2018-04-25","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":0,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/yolov3-an-incremental-improvement","title":"YOLOv3: An Incremental Improvement","date":"2018-04-08","rows_on_this_dataset":1,"code_links":311,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":124,"samples_ran":18,"samples_unverified":106,"pointer_only_for_licence":19,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/low-latency-video-semantic-segmentation","title":"Low-Latency Video Semantic Segmentation","date":"2018-04-02","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/adaptive-affinity-fields-for-semantic","title":"Adaptive Affinity Fields for Semantic Segmentation","date":"2018-03-27","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/espnet-efficient-spatial-pyramid-of-dilated","title":"ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation","date":"2018-03-19","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":4,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dynamic-structured-semantic-propagation","title":"Dynamic-structured Semantic Propagation Network","date":"2018-03-16","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/adversarial-learning-for-semi-supervised","title":"Adversarial Learning for Semi-Supervised Semantic Segmentation","date":"2018-02-22","rows_on_this_dataset":3,"code_links":13,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/stochastic-video-generation-with-a-learned","title":"Stochastic Video Generation with a Learned Prior","date":"2018-02-21","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/encoder-decoder-with-atrous-separable","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","date":"2018-02-07","rows_on_this_dataset":1,"code_links":78,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":72,"samples_ran":43,"samples_unverified":29,"pointer_only_for_licence":40,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/panoptic-segmentation","title":"Panoptic Segmentation","date":"2018-01-03","rows_on_this_dataset":1,"code_links":9,"syntology":null},{"paper":"/paper/high-resolution-image-synthesis-and-semantic","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","date":"2017-11-30","rows_on_this_dataset":1,"code_links":21,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/erfnet-efficient-residual-factorized-convnet","title":"ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation","date":"2017-10-09","rows_on_this_dataset":2,"code_links":13,"syntology":null},{"paper":"/paper/random-erasing-data-augmentation","title":"Random Erasing Data Augmentation","date":"2017-08-16","rows_on_this_dataset":1,"code_links":18,"syntology":null},{"paper":"/paper/semantic-instance-segmentation-with-a","title":"Semantic Instance Segmentation with a Discriminative Loss Function","date":"2017-08-08","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/photographic-image-synthesis-with-cascaded","title":"Photographic Image Synthesis with Cascaded Refinement Networks","date":"2017-07-28","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/rethinking-atrous-convolution-for-semantic","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","date":"2017-06-17","rows_on_this_dataset":2,"code_links":77,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":3,"samples_unverified":4,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/casenet-deep-category-aware-semantic-edge","title":"CASENet: Deep Category-Aware Semantic Edge Detection","date":"2017-05-27","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":3,"samples_unverified":4,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/the-lovasz-softmax-loss-a-tractable-surrogate","title":"The Lovász-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks","date":"2017-05-24","rows_on_this_dataset":2,"code_links":4,"syntology":null},{"paper":"/paper/recurrent-scene-parsing-with-perspective","title":"Recurrent Scene Parsing with Perspective Understanding in the Loop","date":"2017-05-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/icnet-for-real-time-semantic-segmentation-on","title":"ICNet for Real-Time Semantic Segmentation on High-Resolution Images","date":"2017-04-27","rows_on_this_dataset":2,"code_links":18,"syntology":null},{"paper":"/paper/pixelwise-instance-segmentation-with-a","title":"Pixelwise Instance Segmentation with a Dynamically Instantiated Network","date":"2017-04-07","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/unpaired-image-to-image-translation-using","title":"Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks","date":"2017-03-30","rows_on_this_dataset":2,"code_links":190,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":31,"samples_ran":6,"samples_unverified":25,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mask-r-cnn","title":"Mask R-CNN","date":"2017-03-20","rows_on_this_dataset":1,"code_links":179,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":140,"samples_ran":42,"samples_unverified":98,"pointer_only_for_licence":23,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/understanding-convolution-for-semantic","title":"Understanding Convolution for Semantic Segmentation","date":"2017-02-27","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/video-frame-synthesis-using-deep-voxel-flow","title":"Video Frame Synthesis using Deep Voxel Flow","date":"2017-02-08","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/semantic-video-segmentation-by-gated","title":"Semantic Video Segmentation by Gated Recurrent Flow Propagation","date":"2016-12-28","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-from-simulated-and-unsupervised","title":"Learning from Simulated and Unsupervised Images through Adversarial Training","date":"2016-12-22","rows_on_this_dataset":2,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":2,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pyramid-scene-parsing-network","title":"Pyramid Scene Parsing Network","date":"2016-12-04","rows_on_this_dataset":5,"code_links":67,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":29,"samples_ran":7,"samples_unverified":22,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/wider-or-deeper-revisiting-the-resnet-model","title":"Wider or Deeper: Revisiting the ResNet Model for Visual Recognition","date":"2016-11-30","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/full-resolution-residual-networks-for","title":"Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes","date":"2016-11-24","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deep-watershed-transform-for-instance","title":"Deep Watershed Transform for Instance Segmentation","date":"2016-11-24","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":0,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deep-feature-flow-for-video-recognition","title":"Deep Feature Flow for Video Recognition","date":"2016-11-23","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/image-to-image-translation-with-conditional","title":"Image-to-Image Translation with Conditional Adversarial Networks","date":"2016-11-21","rows_on_this_dataset":2,"code_links":192,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":122,"samples_ran":14,"samples_unverified":108,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/refinenet-multi-path-refinement-networks-for","title":"RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation","date":"2016-11-20","rows_on_this_dataset":1,"code_links":13,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":1,"samples_unverified":6,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/coupled-generative-adversarial-networks","title":"Coupled Generative Adversarial Networks","date":"2016-06-24","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/enet-a-deep-neural-network-architecture-for","title":"ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation","date":"2016-06-07","rows_on_this_dataset":2,"code_links":49,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":30,"samples_ran":5,"samples_unverified":25,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deeplab-semantic-image-segmentation-with-deep","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","date":"2016-06-02","rows_on_this_dataset":1,"code_links":47,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":63,"samples_ran":28,"samples_unverified":35,"pointer_only_for_licence":16,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/adversarially-learned-inference","title":"Adversarially Learned Inference","date":"2016-06-02","rows_on_this_dataset":2,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":2,"samples_unverified":2,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fully-convolutional-networks-for-semantic","title":"Fully Convolutional Networks for Semantic Segmentation","date":"2016-05-20","rows_on_this_dataset":2,"code_links":37,"syntology":null},{"paper":"/paper/laplacian-pyramid-reconstruction-and","title":"Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation","date":"2016-05-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/deep-residual-learning-for-image-recognition","title":"Deep Residual Learning for Image Recognition","date":"2015-12-10","rows_on_this_dataset":1,"code_links":484,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":377,"samples_ran":230,"samples_unverified":147,"pointer_only_for_licence":187,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/multi-scale-context-aggregation-by-dilated","title":"Multi-Scale Context Aggregation by Dilated Convolutions","date":"2015-11-23","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":2,"samples_unverified":6,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/segnet-a-deep-convolutional-encoder-decoder","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","date":"2015-11-02","rows_on_this_dataset":1,"code_links":74,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":44,"samples_ran":9,"samples_unverified":35,"pointer_only_for_licence":10,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/semantic-image-segmentation-via-deep-parsing","title":"Semantic Image Segmentation via Deep Parsing Network","date":"2015-09-09","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/faster-r-cnn-towards-real-time-object","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","date":"2015-06-04","rows_on_this_dataset":1,"code_links":196,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":124,"samples_ran":59,"samples_unverified":65,"pointer_only_for_licence":42,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/efficient-piecewise-training-of-deep","title":"Efficient piecewise training of deep structured models for semantic segmentation","date":"2015-04-04","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/conditional-random-fields-as-recurrent-neural-1","title":"Conditional Random Fields as Recurrent Neural Networks","date":"2015-02-11","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":1,"samples_unverified":7,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/semantic-image-segmentation-with-deep","title":"Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs","date":"2014-12-22","rows_on_this_dataset":2,"code_links":18,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/in-defence-of-metric-learning-for-speaker","title":"In defence of metric learning for speaker recognition","date":null,"rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":131,"samples_harvested":2379,"samples_ran":967,"samples_unverified":1412,"pointer_only_for_licence":649,"papers_with_no_sample_that_ran":21,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}