{"url":"/task/image-segmentation","name":"Image Segmentation","slug":"image-segmentation","description_markdown":"**Image Segmentation** is a computer vision task that involves dividing an image into multiple segments or regions, each of which corresponds to a different object or part of an object. The goal of image segmentation is to assign a unique label or category to each pixel in the image, so that pixels with similar attributes are grouped together.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":5035,"papers_with_code":2073,"benchmarks":13,"benchmark_tables_in_archive":13,"benchmark_tables_shown":13,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":43,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/image-segmentation-on-msd-mirror-segmentation","slug":"image-segmentation-on-msd-mirror-segmentation","dataset":"MSD (Mirror Segmentation Dataset)","dataset_url":"/dataset/msd-mirror","rows_in_archive":5,"metrics":["IoU","F-measure","MAE"],"first_row_in_archive_order":{"model":"SAM2-UNet","paper_title":"SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation","paper_url":"/paper/sam2-unet-segment-anything-2-makes-strong","paper_date":"2024-08-16","arxiv_id":"2408.08870","code_links":[{"title":"wzh0120/sam2-unet","url":"https://github.com/wzh0120/sam2-unet"}],"syntology":{"n":9,"n_ran":5,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/image-segmentation-on-pmd","slug":"image-segmentation-on-pmd","dataset":"PMD","dataset_url":"/dataset/pmd","rows_in_archive":5,"metrics":["IoU","F-measure","MAE"],"first_row_in_archive_order":{"model":"SAM2-UNet","paper_title":"SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation","paper_url":"/paper/sam2-unet-segment-anything-2-makes-strong","paper_date":"2024-08-16","arxiv_id":"2408.08870","code_links":[{"title":"wzh0120/sam2-unet","url":"https://github.com/wzh0120/sam2-unet"}],"syntology":{"n":9,"n_ran":5,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/image-segmentation-on-mas3k","slug":"image-segmentation-on-mas3k","dataset":"MAS3K","dataset_url":"/dataset/mas3k","rows_in_archive":4,"metrics":["mIoU","S-measure","E-measure","MAE"],"first_row_in_archive_order":{"model":"SAM2-UNet","paper_title":"SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation","paper_url":"/paper/sam2-unet-segment-anything-2-makes-strong","paper_date":"2024-08-16","arxiv_id":"2408.08870","code_links":[{"title":"wzh0120/sam2-unet","url":"https://github.com/wzh0120/sam2-unet"}],"syntology":{"n":9,"n_ran":5,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/image-segmentation-on-pascal-panoptic-parts","slug":"image-segmentation-on-pascal-panoptic-parts","dataset":"Pascal Panoptic Parts","dataset_url":"/dataset/pascal-panoptic-parts","rows_in_archive":4,"metrics":["mIoUPartS"],"first_row_in_archive_order":{"model":"HIPIE (ViT-H)","paper_title":"Hierarchical Open-vocabulary Universal Image Segmentation","paper_url":"/paper/hierarchical-open-vocabulary-universal-image-1","paper_date":"2023-07-03","arxiv_id":"2307.00764","code_links":[{"title":"berkeley-hipie/hipie","url":"https://github.com/berkeley-hipie/hipie"}],"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/image-segmentation-on-rmas","slug":"image-segmentation-on-rmas","dataset":"RMAS","dataset_url":"/dataset/rmas","rows_in_archive":4,"metrics":["mIoU","S-measure","E-measure","MAE"],"first_row_in_archive_order":{"model":"MAS-SAM","paper_title":"MAS-SAM: Segment Any Marine Animal with Aggregated Features","paper_url":"/paper/mas-sam-segment-any-marine-animal-with","paper_date":"2024-04-24","arxiv_id":"2404.15700","code_links":[{"title":"drchip61/mas-sam","url":"https://github.com/drchip61/mas-sam"}],"syntology":{"n":20,"n_ran":12,"n_unverified":8,"n_pointer_only":20}}},{"leaderboard":"/sota/image-segmentation-on-pascal-voc","slug":"image-segmentation-on-pascal-voc","dataset":"PASCAL VOC","dataset_url":"/dataset/pascal-voc","rows_in_archive":3,"metrics":["mIoU","mAP0.5"],"first_row_in_archive_order":{"model":"OneNete,4-C","paper_title":"OneNet: A Channel-Wise 1D Convolutional U-Net","paper_url":"/paper/onenet-a-channel-wise-1d-convolutional-u-net","paper_date":"2024-11-14","arxiv_id":"2411.09838","code_links":[{"title":"shbyun080/onenet","url":"https://github.com/shbyun080/onenet"}],"syntology":null}},{"leaderboard":"/sota/image-segmentation-on-hutu-80","slug":"image-segmentation-on-hutu-80","dataset":"HuTu 80","dataset_url":"/dataset/hutu-80","rows_in_archive":2,"metrics":["Dice"],"first_row_in_archive_order":{"model":"UNetR","paper_title":"Segmentation of patchy areas in biomedical images based on local edge density estimation","paper_url":"/paper/segmentation-of-patchy-areas-in-biomedical","paper_date":"2022-09-22","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/image-segmentation-on-marida","slug":"image-segmentation-on-marida","dataset":"MARIDA","dataset_url":"/dataset/marida","rows_in_archive":2,"metrics":["IoU","F1","F1@M"],"first_row_in_archive_order":{"model":"ResAttUNet","paper_title":"ResAttUNet: Detecting Marine Debris using an Attention activated Residual UNet","paper_url":"/paper/resattunet-detecting-marine-debris-using-an","paper_date":"2022-10-16","arxiv_id":"2210.08506","code_links":[{"title":"sheikhazhanmohammed/sadma","url":"https://github.com/sheikhazhanmohammed/sadma"}],"syntology":null}},{"leaderboard":"/sota/image-segmentation-on-coco-val2017","slug":"image-segmentation-on-coco-val2017","dataset":"COCO val2017","dataset_url":null,"rows_in_archive":1,"metrics":["mask AP"],"first_row_in_archive_order":{"model":"SynCo (ResNet-50) 200ep","paper_title":"SynCo: Synthetic Hard Negatives in Contrastive Learning for Better Unsupervised Visual Representations","paper_url":"/paper/synco-synthetic-hard-negatives-in-contrastive","paper_date":"2024-10-03","arxiv_id":"2410.02401","code_links":[{"title":"giakoumoglou/synco","url":"https://github.com/giakoumoglou/synco"}],"syntology":null}},{"leaderboard":"/sota/image-segmentation-on-evd4uav","slug":"image-segmentation-on-evd4uav","dataset":"EVD4UAV","dataset_url":"/dataset/evd4uav","rows_in_archive":1,"metrics":["Detection: Full (mAP@0.5)"],"first_row_in_archive_order":{"model":"yolov8x-seg","paper_title":"EVD4UAV: An Altitude-Sensitive Benchmark to Evade Vehicle Detection in UAV","paper_url":"/paper/evd4uav-an-altitude-sensitive-benchmark-to","paper_date":"2024-03-08","arxiv_id":"2403.05422","code_links":[{"title":"hms97/evd4uav","url":"https://github.com/hms97/evd4uav"}],"syntology":null}},{"leaderboard":"/sota/image-segmentation-on-imagenet","slug":"image-segmentation-on-imagenet","dataset":"ImageNet","dataset_url":"/dataset/imagenet","rows_in_archive":1,"metrics":["GFLOPs"],"first_row_in_archive_order":{"model":"MobileOne-S0","paper_title":"MobileOne: An Improved One millisecond Mobile Backbone","paper_url":"/paper/an-improved-one-millisecond-mobile-backbone","paper_date":"2022-06-08","arxiv_id":"2206.04040","code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"BR-IDL/PaddleViT","url":"https://github.com/BR-IDL/PaddleViT/tree/develop/image_classification/MobileOne"},{"title":"apple/ml-mobileone","url":"https://github.com/apple/ml-mobileone"},{"title":"frgfm/Holocron","url":"https://github.com/frgfm/Holocron"},{"title":"chengpengchen/repghost","url":"https://github.com/chengpengchen/repghost"},{"title":"yakhyo/gaze-estimation","url":"https://github.com/yakhyo/gaze-estimation"},{"title":"federicopozzi33/MobileOne-PyTorch","url":"https://github.com/federicopozzi33/MobileOne-PyTorch"},{"title":"james77777778/keras-image-models","url":"https://github.com/james77777778/keras-image-models"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"}],"syntology":{"n":6,"n_ran":1,"n_unverified":5,"n_pointer_only":2}}},{"leaderboard":"/sota/image-segmentation-on-msd-heart","slug":"image-segmentation-on-msd-heart","dataset":"MSD Heart","dataset_url":null,"rows_in_archive":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"OneNete,4","paper_title":"OneNet: A Channel-Wise 1D Convolutional U-Net","paper_url":"/paper/onenet-a-channel-wise-1d-convolutional-u-net","paper_date":"2024-11-14","arxiv_id":"2411.09838","code_links":[{"title":"shbyun080/onenet","url":"https://github.com/shbyun080/onenet"}],"syntology":null}},{"leaderboard":"/sota/image-segmentation-on-oxfordpets","slug":"image-segmentation-on-oxfordpets","dataset":"OxfordPets","dataset_url":null,"rows_in_archive":1,"metrics":["Dice Score"],"first_row_in_archive_order":{"model":"OneNete,4-C","paper_title":"OneNet: A Channel-Wise 1D Convolutional U-Net","paper_url":"/paper/onenet-a-channel-wise-1d-convolutional-u-net","paper_date":"2024-11-14","arxiv_id":"2411.09838","code_links":[{"title":"shbyun080/onenet","url":"https://github.com/shbyun080/onenet"}],"syntology":null}}],"datasets":[{"url":"/dataset/imagenet","name":"ImageNet","full_name":"","num_papers_in_archive":15430},{"url":"/dataset/pascal-voc","name":"PASCAL VOC","full_name":"PASCAL Visual Object Classes Challenge","num_papers_in_archive":198},{"url":"/dataset/sa-1b","name":"SA-1B","full_name":"","num_papers_in_archive":183},{"url":"/dataset/mcubes","name":"MCubeS","full_name":"Multimodal Material Segmentation Dataset","num_papers_in_archive":19},{"url":"/dataset/pmd","name":"PMD","full_name":"","num_papers_in_archive":18},{"url":"/dataset/wildscenes","name":"WildScenes","full_name":"","num_papers_in_archive":12},{"url":"/dataset/entityseg","name":"EntitySeg","full_name":"","num_papers_in_archive":9},{"url":"/dataset/pascal-panoptic-parts","name":"Pascal Panoptic Parts","full_name":"","num_papers_in_archive":9},{"url":"/dataset/chexmask","name":"CheXmask","full_name":"","num_papers_in_archive":7},{"url":"/dataset/marida","name":"MARIDA","full_name":"Marine Debris Archive","num_papers_in_archive":6},{"url":"/dataset/2detect","name":"2DeteCT","full_name":"2DeteCT - A large 2D expandable, trainable, experimental Computed Tomography dataset for machine learning","num_papers_in_archive":5},{"url":"/dataset/msd-mirror","name":"MSD (Mirror Segmentation Dataset)","full_name":"","num_papers_in_archive":5},{"url":"/dataset/mas3k","name":"MAS3K","full_name":"MAS3K: An Open Dataset for Marine Animal Segmentation","num_papers_in_archive":4},{"url":"/dataset/rmas","name":"RMAS","full_name":"Real-World Marine Animal Segmentation","num_papers_in_archive":4},{"url":"/dataset/usis10k","name":"USIS10K","full_name":"Large-scale Underwater Salient Instance Segmentation Dataset","num_papers_in_archive":4},{"url":"/dataset/uiis10k","name":"UIIS10K","full_name":"General Underwater Image Instance Segmentation dataset 10K","num_papers_in_archive":3},{"url":"/dataset/cabuar","name":"CaBuAr","full_name":"CaBuAr: California Burned Areas dataset","num_papers_in_archive":2},{"url":"/dataset/evd4uav","name":"EVD4UAV","full_name":"","num_papers_in_archive":2},{"url":"/dataset/pothole-mix","name":"Pothole Mix","full_name":"Pothole Mix Semantic Segmentation Dataset for Road Damage Detection and Segmentation","num_papers_in_archive":2},{"url":"/dataset/a-collection-of-x-ray-projections-of-131","name":"A collection of X-ray projections of 131 pieces of modeling clay containing stones for machine learning-driven object detection","full_name":"","num_papers_in_archive":1},{"url":"/dataset/bd-typosat","name":"BD-TypoSAT","full_name":"Building Damage Typology Satellite Dataset","num_papers_in_archive":1},{"url":"/dataset/cems-w","name":"CEMS-W","full_name":"CEMS Wildires","num_papers_in_archive":1},{"url":"/dataset/ebhi-seg","name":"EBHI-Seg","full_name":"","num_papers_in_archive":1},{"url":"/dataset/enseg","name":"ENSeg","full_name":"","num_papers_in_archive":1},{"url":"/dataset/fmars","name":"FMARS","full_name":"Foundation Models Annotation in Remote Sensing","num_papers_in_archive":1},{"url":"/dataset/gensc-6g","name":"GenSC-6G","full_name":"","num_papers_in_archive":1},{"url":"/dataset/gf-pa66-3d-xct-latest","name":"GF-PA66 3D XCT (latest)","full_name":"Glass fiber-reinforced polyamide 66 3D X-ray Computed Tomography","num_papers_in_archive":1},{"url":"/dataset/hutu-80","name":"HuTu 80","full_name":"HuTu 80 cell populations","num_papers_in_archive":1},{"url":"/dataset/mineralimage5k","name":"MineralImage5k","full_name":"Benchmark for 5k raw mineral species recognition","num_papers_in_archive":1},{"url":"/dataset/multiraw","name":"multiRAW","full_name":"","num_papers_in_archive":1},{"url":"/dataset/panoramic-video-panoptic-segmentation-dataset","name":"Panoramic Video Panoptic Segmentation Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/potato-a-dataset-for-analyzing-polarimetric","name":"PoTATO: A Dataset for Analyzing Polarimetric Traces of Afloat Trash Objects","full_name":"PoTATO: A Dataset for Analyzing Polarimetric Traces of Afloat Trash Objects","num_papers_in_archive":1},{"url":"/dataset/raw-microscopy-and-raw-drone","name":"Raw-Microscopy and Raw-Drone","full_name":"","num_papers_in_archive":1},{"url":"/dataset/spada-dataset","name":"SPADA Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/the-hypso-1-sea-land-cloud-labeled-dataset","name":"The HYPSO-1 Sea-Land-Cloud-Labeled Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/tomosam","name":"TomoSAM","full_name":"","num_papers_in_archive":1},{"url":"/dataset/uv6k","name":"UV6K","full_name":"Urban Vehicle Segmentation Dataset","num_papers_in_archive":1},{"url":"/dataset/cornhub","name":"CornHub","full_name":"Instance-Segmentation Dataset of Corn Cobs","num_papers_in_archive":0},{"url":"/dataset/iitkgp-fence-dataset","name":"IITKGP_Fence Dataset","full_name":"","num_papers_in_archive":0},{"url":"/dataset/linear-equation-image-dataset","name":"Linear Equation Image Dataset","full_name":"","num_papers_in_archive":0},{"url":"/dataset/sander-jyhne","name":"MapAI Dataset","full_name":"","num_papers_in_archive":0},{"url":"/dataset/primitive-shape-abstraction","name":"Primitive Shape Abstraction","full_name":"","num_papers_in_archive":0},{"url":"/dataset/smdg","name":"SMDG","full_name":"Standardized Multi-Channel Dataset for Glaucoma","num_papers_in_archive":0}],"subtasks":[{"url":"/task/few-shot-instance-segmentation","name":"Few-shot Instance Segmentation"}],"parent_tasks":[{"url":"/task/2d-semantic-segmentation","name":"2D Semantic Segmentation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":2073,"tagged_in_all":5035,"items":[{"url":"/paper/u-net-convolutional-networks-for-biomedical","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","date":"2015-05-18","arxiv_id":"1505.04597","repositories_listed":487,"syntology":{"n":757,"n_ran":510,"n_unverified":247,"n_pointer_only":426}},{"url":"/paper/mobilenetv2-inverted-residuals-and-linear","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","date":"2018-01-13","arxiv_id":"1801.04381","repositories_listed":159,"syntology":{"n":111,"n_ran":85,"n_unverified":26,"n_pointer_only":64}},{"url":"/paper/encoder-decoder-with-atrous-separable","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","date":"2018-02-07","arxiv_id":"1802.02611","repositories_listed":78,"syntology":{"n":72,"n_ran":43,"n_unverified":29,"n_pointer_only":40}},{"url":"/paper/rethinking-atrous-convolution-for-semantic","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","date":"2017-06-17","arxiv_id":"1706.05587","repositories_listed":77,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":3}},{"url":"/paper/segnet-a-deep-convolutional-encoder-decoder","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","date":"2015-11-02","arxiv_id":"1511.00561","repositories_listed":74,"syntology":{"n":44,"n_ran":9,"n_unverified":35,"n_pointer_only":10}},{"url":"/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","arxiv_id":"1606.00915","repositories_listed":47,"syntology":{"n":63,"n_ran":28,"n_unverified":35,"n_pointer_only":16}},{"url":"/paper/attention-u-net-learning-where-to-look-for","title":"Attention U-Net: Learning Where to Look for the Pancreas","date":"2018-04-11","arxiv_id":"1804.03999","repositories_listed":37,"syntology":{"n":28,"n_ran":8,"n_unverified":20,"n_pointer_only":7}},{"url":"/paper/unet-a-nested-u-net-architecture-for-medical","title":"UNet++: A Nested U-Net Architecture for Medical Image Segmentation","date":"2018-07-18","arxiv_id":"1807.10165","repositories_listed":34,"syntology":{"n":28,"n_ran":5,"n_unverified":23,"n_pointer_only":2}},{"url":"/paper/segment-anything","title":"Segment Anything","date":"2023-04-05","arxiv_id":"2304.02643","repositories_listed":32,"syntology":{"n":23,"n_ran":8,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/v-net-fully-convolutional-neural-networks-for","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","date":"2016-06-15","arxiv_id":"1606.04797","repositories_listed":28,"syntology":{"n":22,"n_ran":2,"n_unverified":20,"n_pointer_only":0}},{"url":"/paper/fast-scnn-fast-semantic-segmentation-network","title":"Fast-SCNN: Fast Semantic Segmentation Network","date":"2019-02-12","arxiv_id":"1902.04502","repositories_listed":24,"syntology":{"n":32,"n_ran":0,"n_unverified":32,"n_pointer_only":0}},{"url":"/paper/the-one-hundred-layers-tiramisu-fully","title":"The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation","date":"2016-11-28","arxiv_id":"1611.09326","repositories_listed":23,"syntology":{"n":24,"n_ran":1,"n_unverified":23,"n_pointer_only":6}},{"url":"/paper/transunet-transformers-make-strong-encoders","title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","date":"2021-02-08","arxiv_id":"2102.04306","repositories_listed":22,"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":7}},{"url":"/paper/semantic-image-segmentation-with-deep","title":"Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs","date":"2014-12-22","arxiv_id":"1412.7062","repositories_listed":18,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/how-to-train-your-vit-data-augmentation-and","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","date":"2021-06-18","arxiv_id":"2106.10270","repositories_listed":16,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/pointrend-image-segmentation-as-rendering","title":"PointRend: Image Segmentation as Rendering","date":"2019-12-17","arxiv_id":"1912.08193","repositories_listed":14,"syntology":{"n":18,"n_ran":5,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/unet-redesigning-skip-connections-to-exploit","title":"UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation","date":"2019-12-11","arxiv_id":"1912.05074","repositories_listed":13,"syntology":{"n":9,"n_ran":1,"n_unverified":8,"n_pointer_only":2}},{"url":"/paper/ternausnet-u-net-with-vgg11-encoder-pre","title":"TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation","date":"2018-01-17","arxiv_id":"1801.05746","repositories_listed":13,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/uncertainty-aware-self-ensembling-model-for","title":"Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation","date":"2019-07-16","arxiv_id":"1907.07034","repositories_listed":12,"syntology":{"n":15,"n_ran":8,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/auto-deeplab-hierarchical-neural-architecture","title":"Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation","date":"2019-01-10","arxiv_id":"1901.02985","repositories_listed":12,"syntology":{"n":4,"n_ran":1,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/recurrent-residual-convolutional-neural","title":"Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation","date":"2018-02-20","arxiv_id":"1802.06955","repositories_listed":12,"syntology":{"n":8,"n_ran":5,"n_unverified":3,"n_pointer_only":5}},{"url":"/paper/2408-00714","title":"SAM 2: Segment Anything in Images and Videos","date":"2024-08-01","arxiv_id":"2408.00714","repositories_listed":11,"syntology":{"n":49,"n_ran":28,"n_unverified":21,"n_pointer_only":0}},{"url":"/paper/w-net-a-deep-model-for-fully-unsupervised","title":"W-Net: A Deep Model for Fully Unsupervised Image Segmentation","date":"2017-11-22","arxiv_id":"1711.08506","repositories_listed":11,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/an-improved-one-millisecond-mobile-backbone","title":"MobileOne: An Improved One millisecond Mobile Backbone","date":"2022-06-08","arxiv_id":"2206.04040","repositories_listed":10,"syntology":{"n":6,"n_ran":1,"n_unverified":5,"n_pointer_only":2}},{"url":"/paper/mask-dino-towards-a-unified-transformer-based-1","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","date":"2022-06-06","arxiv_id":"2206.02777","repositories_listed":10,"syntology":{"n":13,"n_ran":11,"n_unverified":2,"n_pointer_only":13}},{"url":"/paper/unetr-transformers-for-3d-medical-image","title":"UNETR: Transformers for 3D Medical Image Segmentation","date":"2021-03-18","arxiv_id":"2103.10504","repositories_listed":10,"syntology":null},{"url":"/paper/nnu-net-self-adapting-framework-for-u-net","title":"nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation","date":"2018-09-27","arxiv_id":"1809.10486","repositories_listed":9,"syntology":{"n":11,"n_ran":3,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/concurrent-spatial-and-channel-squeeze","title":"Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks","date":"2018-03-07","arxiv_id":"1803.02579","repositories_listed":9,"syntology":null},{"url":"/paper/panoptic-segmentation","title":"Panoptic Segmentation","date":"2018-01-03","arxiv_id":"1801.00868","repositories_listed":9,"syntology":null},{"url":"/paper/segmenter-transformer-for-semantic","title":"Segmenter: Transformer for Semantic Segmentation","date":"2021-05-12","arxiv_id":"2105.05633","repositories_listed":8,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}}],"syntology_records":27,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}