{"url":"/sota/semantic-segmentation-on-densepass","task":{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","note":null},"dataset":{"name":"DensePASS","url":"/dataset/densepass"},"category":"Computer Vision","categories":["Computer Code","Computer Vision","Medical","Robots"],"category_note":null,"description":null,"description_from":null,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["mIoU"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"mIoU":null}},"counts":{"rows":36,"rows_with_code":36,"rows_with_paper_page":36,"rows_dated":36,"rows_using_additional_data":6},"rows":[{"rank_in_archive_order":1,"model":"Trans4PASS+ (multi-scale)","metrics":{"mIoU":"57.23%"},"uses_additional_data":false,"paper_date":"2022-07-25","paper":"/paper/behind-every-domain-there-is-a-shift-adapting","paper_url":"https://arxiv.org/abs/2207.11860v5","paper_title":"Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation","code":"https://github.com/jamycheung/trans4pass","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"Trans4PASS+ (single-scale)","metrics":{"mIoU":"56.45%"},"uses_additional_data":false,"paper_date":"2022-07-25","paper":"/paper/behind-every-domain-there-is-a-shift-adapting","paper_url":"https://arxiv.org/abs/2207.11860v5","paper_title":"Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation","code":"https://github.com/jamycheung/trans4pass","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"Trans4PASS (multi-scale)","metrics":{"mIoU":"56.38%"},"uses_additional_data":false,"paper_date":"2022-03-02","paper":"/paper/bending-reality-distortion-aware-transformers","paper_url":"https://arxiv.org/abs/2203.01452v2","paper_title":"Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation","code":"https://github.com/jamycheung/trans4pass","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"Trans4PASS (single-scale)","metrics":{"mIoU":"55.25%"},"uses_additional_data":false,"paper_date":"2022-03-02","paper":"/paper/bending-reality-distortion-aware-transformers","paper_url":"https://arxiv.org/abs/2203.01452v2","paper_title":"Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation","code":"https://github.com/jamycheung/trans4pass","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"DAFormer","metrics":{"mIoU":"54.67%"},"uses_additional_data":false,"paper_date":"2021-11-29","paper":"/paper/daformer-improving-network-architectures-and","paper_url":"https://arxiv.org/abs/2111.14887v2","paper_title":"DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation","code":"https://github.com/lhoyer/DAFormer","n_code_links":3,"syntology":{"n_ran":6,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":6,"model":"PCS","metrics":{"mIoU":"53.83%"},"uses_additional_data":false,"paper_date":"2021-03-31","paper":"/paper/prototypical-cross-domain-self-supervised","paper_url":"https://arxiv.org/abs/2103.16765v1","paper_title":"Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation","code":"https://github.com/zhengzangw/PCS-FUDA","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"P2PDA (Cityscapes+WildDash)","metrics":{"mIoU":"48.52%"},"uses_additional_data":true,"paper_date":"2021-10-21","paper":"/paper/transfer-beyond-the-field-of-view-dense","paper_url":"https://arxiv.org/abs/2110.11062v1","paper_title":"Transfer beyond the Field of View: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation","code":"https://github.com/chma1024/densepass","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"SIM","metrics":{"mIoU":"44.58%"},"uses_additional_data":false,"paper_date":"2020-03-18","paper":"/paper/differential-treatment-for-stuff-and-things-a","paper_url":"https://arxiv.org/abs/2003.08040v3","paper_title":"Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation","code":"https://github.com/SHI-Labs/Unsupervised-Domain-Adaptation-with-Differential-Treatment","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":9,"model":"PoolFormer (MiT-B1)","metrics":{"mIoU":"43.18%"},"uses_additional_data":false,"paper_date":"2021-11-22","paper":"/paper/metaformer-is-actually-what-you-need-for","paper_url":"https://arxiv.org/abs/2111.11418v3","paper_title":"MetaFormer Is Actually What You Need for Vision","code":"https://github.com/huggingface/transformers","n_code_links":18,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"ECANet","metrics":{"mIoU":"43.02%"},"uses_additional_data":true,"paper_date":"2021-03-09","paper":"/paper/capturing-omni-range-context-for","paper_url":"https://arxiv.org/abs/2103.05687v1","paper_title":"Capturing Omni-Range Context for Omnidirectional Segmentation","code":"https://github.com/elnino9ykl/WildPASS","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"FAN (MiT-B1)","metrics":{"mIoU":"42.54%"},"uses_additional_data":false,"paper_date":"2022-04-26","paper":"/paper/understanding-the-robustness-in-vision","paper_url":"https://arxiv.org/abs/2204.12451v4","paper_title":"Understanding The Robustness in Vision Transformers","code":"https://github.com/nvlabs/fan","n_code_links":2,"syntology":null},{"rank_in_archive_order":12,"model":"SegFormer (MiT-B2)","metrics":{"mIoU":"42.4%"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/segformer-simple-and-efficient-design-for","paper_url":"https://arxiv.org/abs/2105.15203v3","paper_title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","code":"https://github.com/huggingface/transformers","n_code_links":28,"syntology":{"n_ran":48,"n_unverified":38,"n_samples":86,"n_pointer_only_licence":15}},{"rank_in_archive_order":13,"model":"ASMLP (MiT-B1)","metrics":{"mIoU":"42.05%"},"uses_additional_data":false,"paper_date":"2021-07-18","paper":"/paper/as-mlp-an-axial-shifted-mlp-architecture-for","paper_url":"https://arxiv.org/abs/2107.08391v2","paper_title":"AS-MLP: An Axial Shifted MLP Architecture for Vision","code":"https://github.com/liuruiyang98/Jittor-MLP","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":8,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"P2PDA (Cityscapes)","metrics":{"mIoU":"41.99%"},"uses_additional_data":false,"paper_date":"2021-10-21","paper":"/paper/transfer-beyond-the-field-of-view-dense","paper_url":"https://arxiv.org/abs/2110.11062v1","paper_title":"Transfer beyond the Field of View: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation","code":"https://github.com/chma1024/densepass","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"CycleMLP (MiT-B1)","metrics":{"mIoU":"40.16%"},"uses_additional_data":false,"paper_date":"2021-07-21","paper":"/paper/cyclemlp-a-mlp-like-architecture-for-dense","paper_url":"https://arxiv.org/abs/2107.10224v4","paper_title":"CycleMLP: A MLP-like Architecture for Dense Prediction","code":"https://github.com/BR-IDL/PaddleViT","n_code_links":8,"syntology":{"n_ran":8,"n_unverified":7,"n_samples":15,"n_pointer_only_licence":1}},{"rank_in_archive_order":16,"model":"SegFormer (MiT-B1)","metrics":{"mIoU":"38.5%"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/segformer-simple-and-efficient-design-for","paper_url":"https://arxiv.org/abs/2105.15203v3","paper_title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","code":"https://github.com/huggingface/transformers","n_code_links":28,"syntology":{"n_ran":48,"n_unverified":38,"n_samples":86,"n_pointer_only_licence":15}},{"rank_in_archive_order":17,"model":"DPT (MiT-B1)","metrics":{"mIoU":"36.50%"},"uses_additional_data":false,"paper_date":"2021-07-30","paper":"/paper/dpt-deformable-patch-based-transformer-for","paper_url":"https://arxiv.org/abs/2107.14467v1","paper_title":"DPT: Deformable Patch-based Transformer for Visual Recognition","code":"https://github.com/CASIA-IVA-Lab/DPT","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"SETR (PUP, Transformer-L)","metrics":{"mIoU":"35.7%"},"uses_additional_data":false,"paper_date":"2020-12-31","paper":"/paper/rethinking-semantic-segmentation-from-a","paper_url":"https://arxiv.org/abs/2012.15840v3","paper_title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":5,"syntology":null},{"rank_in_archive_order":19,"model":"SETR (MLA, Transformer-L)","metrics":{"mIoU":"35.6%"},"uses_additional_data":false,"paper_date":"2020-12-31","paper":"/paper/rethinking-semantic-segmentation-from-a","paper_url":"https://arxiv.org/abs/2012.15840v3","paper_title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":5,"syntology":null},{"rank_in_archive_order":20,"model":"Seamless (Mapillary)","metrics":{"mIoU":"34.14%"},"uses_additional_data":true,"paper_date":"2019-05-03","paper":"/paper/seamless-scene-segmentation","paper_url":"https://arxiv.org/abs/1905.01220v1","paper_title":"Seamless Scene Segmentation","code":"https://github.com/mapillary/seamseg","n_code_links":5,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":21,"model":"DeepLabV3+ (ResNet-101)","metrics":{"mIoU":"32.5%"},"uses_additional_data":false,"paper_date":"2018-02-07","paper":"/paper/encoder-decoder-with-atrous-separable","paper_url":"http://arxiv.org/abs/1802.02611v3","paper_title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","code":"https://github.com/tensorflow/models/tree/master/research/deeplab","n_code_links":78,"syntology":{"n_ran":43,"n_unverified":29,"n_samples":72,"n_pointer_only_licence":40}},{"rank_in_archive_order":22,"model":"DNL (ResNet-101)","metrics":{"mIoU":"32.1%"},"uses_additional_data":false,"paper_date":"2020-06-11","paper":"/paper/disentangled-non-local-neural-networks","paper_url":"https://arxiv.org/abs/2006.06668v2","paper_title":"Disentangled Non-Local Neural Networks","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":5,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":23,"model":"SwiftNet (Merge3)","metrics":{"mIoU":"32.04%"},"uses_additional_data":true,"paper_date":"2020-08-20","paper":"/paper/issafe-improving-semantic-segmentation-in","paper_url":"https://arxiv.org/abs/2008.08974v2","paper_title":"ISSAFE: Improving Semantic Segmentation in Accidents by Fusing Event-based Data","code":"https://github.com/jamycheung/ISSAFE","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"CRST","metrics":{"mIoU":"31.67%"},"uses_additional_data":false,"paper_date":"2019-08-26","paper":"/paper/confidence-regularized-self-training","paper_url":"https://arxiv.org/abs/1908.09822v3","paper_title":"Confidence Regularized Self-Training","code":"https://github.com/yzou2/CRST","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":25,"model":"CLAN","metrics":{"mIoU":"31.46%"},"uses_additional_data":false,"paper_date":"2018-09-25","paper":"/paper/taking-a-closer-look-at-domain-shift-category","paper_url":"http://arxiv.org/abs/1809.09478v3","paper_title":"Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation","code":"https://github.com/RoyalVane/CLAN","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":6,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":26,"model":"PVT (Tiny, FPN)","metrics":{"mIoU":"31.20%"},"uses_additional_data":false,"paper_date":"2021-02-24","paper":"/paper/pyramid-vision-transformer-a-versatile","paper_url":"https://arxiv.org/abs/2102.12122v2","paper_title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","code":"https://github.com/open-mmlab/mmdetection","n_code_links":11,"syntology":{"n_ran":22,"n_unverified":8,"n_samples":30,"n_pointer_only_licence":1}},{"rank_in_archive_order":27,"model":"USSS (Mapillary)","metrics":{"mIoU":"30.87%"},"uses_additional_data":true,"paper_date":"2018-11-26","paper":"/paper/universal-semi-supervised-semantic","paper_url":"https://arxiv.org/abs/1811.10323v3","paper_title":"Universal Semi-Supervised Semantic Segmentation","code":"https://github.com/tarun005/USSS_ICCV19","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"PSPNet (ResNet-50)","metrics":{"mIoU":"29.5%"},"uses_additional_data":false,"paper_date":"2016-12-04","paper":"/paper/pyramid-scene-parsing-network","paper_url":"http://arxiv.org/abs/1612.01105v2","paper_title":"Pyramid Scene Parsing Network","code":"https://github.com/tensorflow/models","n_code_links":67,"syntology":{"n_ran":7,"n_unverified":22,"n_samples":29,"n_pointer_only_licence":5}},{"rank_in_archive_order":29,"model":"Semantic-FPN (ResNet-101)","metrics":{"mIoU":"28.8%"},"uses_additional_data":false,"paper_date":"2019-01-08","paper":"/paper/panoptic-feature-pyramid-networks","paper_url":"http://arxiv.org/abs/1901.02446v2","paper_title":"Panoptic Feature Pyramid Networks","code":"https://github.com/facebookresearch/detectron2","n_code_links":12,"syntology":{"n_ran":7,"n_unverified":5,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":30,"model":"DANet (ResNet-101)","metrics":{"mIoU":"28.5%"},"uses_additional_data":false,"paper_date":"2018-09-09","paper":"/paper/dual-attention-network-for-scene-segmentation","paper_url":"http://arxiv.org/abs/1809.02983v4","paper_title":"Dual Attention Network for Scene Segmentation","code":"https://github.com/xmu-xiaoma666/External-Attention-pytorch","n_code_links":12,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":5}},{"rank_in_archive_order":31,"model":"USSS (IDD)","metrics":{"mIoU":"26.98%"},"uses_additional_data":true,"paper_date":"2018-11-26","paper":"/paper/universal-semi-supervised-semantic","paper_url":"https://arxiv.org/abs/1811.10323v3","paper_title":"Universal Semi-Supervised Semantic Segmentation","code":"https://github.com/tarun005/USSS_ICCV19","n_code_links":1,"syntology":null},{"rank_in_archive_order":32,"model":"FANet (Resnet-34)","metrics":{"mIoU":"26.9%"},"uses_additional_data":false,"paper_date":"2020-07-07","paper":"/paper/real-time-semantic-segmentation-with-fast","paper_url":"https://arxiv.org/abs/2007.03815v2","paper_title":"Real-time Semantic Segmentation with Fast Attention","code":"https://github.com/feinanshan/FANet","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"SwiftNet (Cityscapes)","metrics":{"mIoU":"25.67%"},"uses_additional_data":false,"paper_date":"2019-03-20","paper":"/paper/in-defense-of-pre-trained-imagenet","paper_url":"http://arxiv.org/abs/1903.08469v2","paper_title":"In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images","code":"https://github.com/XuJiacong/PIDNet","n_code_links":6,"syntology":null},{"rank_in_archive_order":34,"model":"Fast-SCNN","metrics":{"mIoU":"24.6%"},"uses_additional_data":false,"paper_date":"2019-02-12","paper":"/paper/fast-scnn-fast-semantic-segmentation-network","paper_url":"http://arxiv.org/abs/1902.04502v1","paper_title":"Fast-SCNN: Fast Semantic Segmentation Network","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":24,"syntology":{"n_ran":0,"n_unverified":32,"n_samples":32,"n_pointer_only_licence":0}},{"rank_in_archive_order":35,"model":"PASS","metrics":{"mIoU":"23.66%"},"uses_additional_data":false,"paper_date":"2019-09-17","paper":"/paper/ds-pass-detail-sensitive-panoramic-annular","paper_url":"https://arxiv.org/abs/1909.07721v2","paper_title":"DS-PASS: Detail-Sensitive Panoramic Annular Semantic Segmentation through SwaftNet for Surrounding Sensing","code":"https://github.com/elnino9ykl/DS-PASS","n_code_links":1,"syntology":null},{"rank_in_archive_order":36,"model":"ERFNet","metrics":{"mIoU":"16.65%"},"uses_additional_data":false,"paper_date":"2017-10-09","paper":"/paper/erfnet-efficient-residual-factorized-convnet","paper_url":"https://ieeexplore.ieee.org/abstract/document/8063438","paper_title":"ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation","code":"https://github.com/osmr/imgclsmob","n_code_links":13,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":20,"rows_with_any_sample_ran":18,"distinct_papers_with_graph_line":19,"distinct_papers_with_any_sample_ran":17,"samples_over_distinct_papers":{"n_ran":170,"n_unverified":170,"n_samples":340,"n_pointer_only_licence":76,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":218,"n_unverified":208,"n_samples":426,"n_pointer_only_licence":91,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}