{"url":"/task/segmentation","name":"Segmentation","slug":"segmentation","description_markdown":null,"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":13072,"papers_with_code":5255,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"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":45,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/segmentation-on-sa-1b","slug":"segmentation-on-sa-1b","dataset":"SA-1B","dataset_url":"/dataset/sa-1b","rows_in_archive":2,"metrics":["Average Precision","AR-small","AR-medium","AR-large"],"first_row_in_archive_order":{"model":"unSAM+ (Semi-supervised)","paper_title":"Segment Anything without Supervision","paper_url":"/paper/segment-anything-without-supervision","paper_date":"2024-06-28","arxiv_id":"2406.20081","code_links":[{"title":"frank-xwang/unsam","url":"https://github.com/frank-xwang/unsam"}],"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":5}}},{"leaderboard":"/sota/segmentation-on","slug":"segmentation-on","dataset":"!(()&&!|*|*|","dataset_url":null,"rows_in_archive":1,"metrics":["10%"],"first_row_in_archive_order":{"model":"HNN","paper_title":"Liver Segmentation from Multimodal Images using HED-Mask R-CNN","paper_url":"/paper/liver-segmentation-from-multimodal-images","paper_date":"2019-10-23","arxiv_id":"1910.10504","code_links":[],"syntology":null}},{"leaderboard":"/sota/segmentation-on-mfsd","slug":"segmentation-on-mfsd","dataset":"MFSD","dataset_url":"/dataset/mfsd","rows_in_archive":1,"metrics":["F1 Score"],"first_row_in_archive_order":{"model":"ABANet","paper_title":"ABANet: Attention boundary-aware network for image segmentation","paper_url":"/paper/abanet-attention-boundary-aware-network-for","paper_date":"2024-05-17","arxiv_id":null,"code_links":[{"title":"Recognito-Vision/Face-SDK-Linux-Demos","url":"https://github.com/Recognito-Vision/Face-SDK-Linux-Demos"},{"title":"sadjadrz/mfsd","url":"https://github.com/sadjadrz/mfsd"}],"syntology":null}},{"leaderboard":"/sota/segmentation-on-mmflood","slug":"segmentation-on-mmflood","dataset":"MMFlood","dataset_url":"/dataset/mmflood","rows_in_archive":1,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"ResNet50 + DeepLabV3+","paper_title":"MMFlood: A Multimodal Dataset for Flood Delineation From Satellite Imagery","paper_url":"/paper/mmflood-a-multimodal-dataset-for-flood","paper_date":"2022-09-02","arxiv_id":null,"code_links":[{"title":"edornd/mmflood","url":"https://github.com/edornd/mmflood"}],"syntology":null}},{"leaderboard":"/sota/segmentation-on-simgas","slug":"segmentation-on-simgas","dataset":"SimGas","dataset_url":"/dataset/simgas","rows_in_archive":1,"metrics":["IoU","Precision","Recall"],"first_row_in_archive_order":{"model":"LangGas","paper_title":"LangGas: Introducing Language in Selective Zero-Shot Background Subtraction for Semi-Transparent Gas Leak Detection with a New Dataset","paper_url":"/paper/langgas-introducing-language-in-selective","paper_date":"2025-03-04","arxiv_id":"2503.02910","code_links":[{"title":"weathon/Lang-Gas","url":"https://github.com/weathon/Lang-Gas"}],"syntology":null}}],"datasets":[{"url":"/dataset/sa-1b","name":"SA-1B","full_name":"","num_papers_in_archive":183},{"url":"/dataset/crack500","name":"CRACK500","full_name":"","num_papers_in_archive":34},{"url":"/dataset/uiis-dataset","name":"UIIS","full_name":"General Underwater Image Instance Segmentation dataset","num_papers_in_archive":9},{"url":"/dataset/robust-mis","name":"ROBUST-MIS","full_name":"Robust Medical Instrument Segmentation Challenge 2019","num_papers_in_archive":8},{"url":"/dataset/25ktrees","name":"25kTrees","full_name":"Individual Tree Crown Annotations","num_papers_in_archive":5},{"url":"/dataset/bhsd","name":"BHSD","full_name":"A 3D Multi-class Brain Hemorrhage Segmentation Dataset","num_papers_in_archive":5},{"url":"/dataset/cc3m-tagmask","name":"CC3M-TagMask","full_name":"","num_papers_in_archive":5},{"url":"/dataset/mmflood","name":"MMFlood","full_name":"MMFlood","num_papers_in_archive":5},{"url":"/dataset/cfd","name":"CFD","full_name":"CrackForestDataset","num_papers_in_archive":4},{"url":"/dataset/crackvision12k","name":"CrackVision12K","full_name":"","num_papers_in_archive":4},{"url":"/dataset/phsyionet-challenge-2024","name":"ECG-Image-Database","full_name":"Digitization and Classification of ECG Images: The George B. Moody PhysioNet Challenge 2024","num_papers_in_archive":4},{"url":"/dataset/khanhha-s-dataset","name":"Khanhha's dataset","full_name":"","num_papers_in_archive":4},{"url":"/dataset/llm-seg40k","name":"LLM-Seg40K","full_name":"LLM-Seg40K","num_papers_in_archive":4},{"url":"/dataset/pastis-r","name":"PASTIS-R","full_name":"Panoptic Segmentation of Radar and Optical Satellite image TIme Series","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/smile-uhura","name":"SMILE-UHURA","full_name":"Small Vessel Segmentation at Mesoscopic Scale from Ultra-High Resolution 7T Magnetic Resonance Angiogram","num_papers_in_archive":3},{"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/covid-qu-ex","name":"COVID-QU-Ex","full_name":"","num_papers_in_archive":2},{"url":"/dataset/segrcdb","name":"SegRCDB","full_name":"","num_papers_in_archive":2},{"url":"/dataset/the-uls23-challenge-test-set","name":"The ULS23 Challenge Test Set","full_name":"","num_papers_in_archive":2},{"url":"/dataset/underwater-trash-detection","name":"Underwater Trash Detection","full_name":"","num_papers_in_archive":2},{"url":"/dataset/aneux","name":"Aneux","full_name":"","num_papers_in_archive":1},{"url":"/dataset/boreal-forest-fire","name":"Boreal Forest Fire","full_name":"Boreal Forest Fire: UAV-collected Wildfire Detection and Smoke Segmentation Dataset","num_papers_in_archive":1},{"url":"/dataset/box-is","name":"Box-IS","full_name":"Box-IS","num_papers_in_archive":1},{"url":"/dataset/brats-peds-2023","name":"BraTS PEDs 2023","full_name":"The Brain Tumor Segmentation (BraTS) Challenge 2023: Focus on Pediatrics (CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs)","num_papers_in_archive":1},{"url":"/dataset/brisc","name":"BRISC","full_name":"BRISC: Annotated Dataset for Brain Tumor Segmentation and Classification","num_papers_in_archive":1},{"url":"/dataset/coil100-augmented","name":"Coil100-Augmented","full_name":"","num_papers_in_archive":1},{"url":"/dataset/cranfield-synthetic-drone-detection","name":"cranfield-synthetic-drone-detection","full_name":"","num_papers_in_archive":1},{"url":"/dataset/cuts","name":"CUTS","full_name":"","num_papers_in_archive":1},{"url":"/dataset/deepcrack","name":"DeepCrack","full_name":"","num_papers_in_archive":1},{"url":"/dataset/extended-task10-colon-medical-decathlon","name":"Extended Task10_Colon Medical Decathlon","full_name":"Extended Task10_Colon of Medical Segmentation Decathlon dataset","num_papers_in_archive":1},{"url":"/dataset/fp4s","name":"FP4S","full_name":"Floor plan image segmentation via scribble-based semi-weakly-supervised learning","num_papers_in_archive":1},{"url":"/dataset/les-av","name":"LES-AV","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mfsd","name":"MFSD","full_name":"Masked Face Segmentation Dataset","num_papers_in_archive":1},{"url":"/dataset/microscopy-image-dataset-of-pulmonary","name":"Microscopy Image Dataset of Pulmonary Vascular Changes","full_name":"Microscopy Image Dataset for Deep Learning-Based Quantitative Assessment of Pulmonary Vascular Changes","num_papers_in_archive":1},{"url":"/dataset/npo","name":"NPO","full_name":"Negative and Positive Obstacles","num_papers_in_archive":1},{"url":"/dataset/nyudv2-is","name":"NYUDv2-IS","full_name":"","num_papers_in_archive":1},{"url":"/dataset/remote-flash-lidar-vehicles-dataset","name":"Remote Flash LiDAR Vehicles Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/s-biad843","name":"S-BIAD843","full_name":"Individual 3D cell shapes of Drosophila Wing Disc","num_papers_in_archive":1},{"url":"/dataset/simgas","name":"SimGas","full_name":"Computer Simulated Gas Leakage Segmentation","num_papers_in_archive":1},{"url":"/dataset/sun-rgbd-is","name":"SUN-RGBD-IS","full_name":"SUN-RGBD-IS","num_papers_in_archive":1},{"url":"/dataset/aachen-heerlen-annotated-steel-microstructure","name":"Aachen-Heerlen Annotated Steel Microstructure Dataset","full_name":"","num_papers_in_archive":0},{"url":"/dataset/palms","name":"PALMS","full_name":"","num_papers_in_archive":0},{"url":"/dataset/tornet","name":"Tornet","full_name":"Tornado Network","num_papers_in_archive":0}],"subtasks":[{"url":"/task/open-vocabulary-semantic-segmentation-1","name":"Open-Vocabulary Semantic Segmentation"}],"parent_tasks":[],"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":5255,"tagged_in_all":13072,"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/mask-r-cnn","title":"Mask R-CNN","date":"2017-03-20","arxiv_id":"1703.06870","repositories_listed":179,"syntology":{"n":140,"n_ran":42,"n_unverified":98,"n_pointer_only":23}},{"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/searching-for-mobilenetv3","title":"Searching for MobileNetV3","date":"2019-05-06","arxiv_id":"1905.02244","repositories_listed":67,"syntology":{"n":105,"n_ran":58,"n_unverified":47,"n_pointer_only":46}},{"url":"/paper/fully-convolutional-networks-for-semantic-1","title":"Fully Convolutional Networks for Semantic Segmentation","date":"2014-11-14","arxiv_id":"1411.4038","repositories_listed":51,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":4}},{"url":"/paper/yolact-real-time-instance-segmentation","title":"YOLACT: Real-time Instance Segmentation","date":"2019-04-04","arxiv_id":"1904.02689","repositories_listed":48,"syntology":{"n":21,"n_ran":10,"n_unverified":11,"n_pointer_only":6}},{"url":"/paper/microsoft-coco-common-objects-in-context","title":"Microsoft COCO: Common Objects in Context","date":"2014-05-01","arxiv_id":"1405.0312","repositories_listed":38,"syntology":{"n":7,"n_ran":1,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/fully-convolutional-networks-for-semantic","title":"Fully Convolutional Networks for Semantic Segmentation","date":"2016-05-20","arxiv_id":"1605.06211","repositories_listed":37,"syntology":null},{"url":"/paper/yolact-better-real-time-instance-segmentation","title":"YOLACT++: Better Real-time Instance Segmentation","date":"2019-12-03","arxiv_id":"1912.06218","repositories_listed":36,"syntology":{"n":43,"n_ran":11,"n_unverified":32,"n_pointer_only":0}},{"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/3d-u-net-learning-dense-volumetric","title":"3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation","date":"2016-06-21","arxiv_id":"1606.06650","repositories_listed":27,"syntology":{"n":76,"n_ran":53,"n_unverified":23,"n_pointer_only":20}},{"url":"/paper/neural-machine-translation-of-rare-words-with","title":"Neural Machine Translation of Rare Words with Subword Units","date":"2015-08-31","arxiv_id":"1508.07909","repositories_listed":26,"syntology":{"n":30,"n_ran":21,"n_unverified":9,"n_pointer_only":21}},{"url":"/paper/point-transformer-1","title":"Point Transformer","date":"2020-12-16","arxiv_id":"2012.09164","repositories_listed":24,"syntology":null},{"url":"/paper/solo-segmenting-objects-by-locations","title":"SOLO: Segmenting Objects by Locations","date":"2019-12-10","arxiv_id":"1912.04488","repositories_listed":24,"syntology":null},{"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-understanding-of-scenes-through-the","title":"Semantic Understanding of Scenes through the ADE20K Dataset","date":"2016-08-18","arxiv_id":"1608.05442","repositories_listed":22,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":1}},{"url":"/paper/visual-attention-network","title":"Visual Attention Network","date":"2022-02-20","arxiv_id":"2202.09741","repositories_listed":21,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/bisenet-bilateral-segmentation-network-for","title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","date":"2018-08-02","arxiv_id":"1808.00897","repositories_listed":21,"syntology":{"n":18,"n_ran":6,"n_unverified":12,"n_pointer_only":1}},{"url":"/paper/bayesian-segnet-model-uncertainty-in-deep","title":"Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding","date":"2015-11-09","arxiv_id":"1511.02680","repositories_listed":21,"syntology":{"n":18,"n_ran":0,"n_unverified":18,"n_pointer_only":0}},{"url":"/paper/solov2-dynamic-faster-and-stronger","title":"SOLOv2: Dynamic and Fast Instance Segmentation","date":"2020-03-23","arxiv_id":"2003.10152","repositories_listed":18,"syntology":{"n":38,"n_ran":15,"n_unverified":23,"n_pointer_only":24}},{"url":"/paper/skin-lesion-analysis-toward-melanoma-1","title":"Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)","date":"2019-02-09","arxiv_id":"1902.03368","repositories_listed":18,"syntology":{"n":17,"n_ran":3,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/icnet-for-real-time-semantic-segmentation-on","title":"ICNet for Real-Time Semantic Segmentation on High-Resolution Images","date":"2017-04-27","arxiv_id":"1704.08545","repositories_listed":18,"syntology":null},{"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/improving-unsupervised-defect-segmentation-by","title":"Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders","date":"2018-07-05","arxiv_id":"1807.02011","repositories_listed":16,"syntology":null},{"url":"/paper/real-time-scene-text-detection-with","title":"Real-time Scene Text Detection with Differentiable Binarization","date":"2019-11-20","arxiv_id":"1911.08947","repositories_listed":15,"syntology":{"n":25,"n_ran":3,"n_unverified":22,"n_pointer_only":0}},{"url":"/paper/multinet-real-time-joint-semantic-reasoning","title":"MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving","date":"2016-12-22","arxiv_id":"1612.07695","repositories_listed":15,"syntology":{"n":42,"n_ran":6,"n_unverified":36,"n_pointer_only":0}}],"syntology_records":25,"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"}}