{"url":"/task/weakly-supervised-semantic-segmentation","name":"Weakly-Supervised Semantic Segmentation","slug":"weakly-supervised-semantic-segmentation","description_markdown":"The semantic segmentation task is to assign a label from a label set to each pixel in an image. In the case of fully supervised setting, the dataset  consists of images and their corresponding\r\npixel-level class-specific annotations (expensive pixel-level annotations). However, in the\r\nweakly-supervised setting, the dataset consists of images and corresponding annotations that\r\nare relatively easy to obtain, such as tags/labels of objects present in the image.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing](http://openaccess.thecvf.com/content_cvpr_2018/papers/Huang_Weakly-Supervised_Semantic_Segmentation_CVPR_2018_paper.pdf) )</span>","categories":[{"name":"Computer Code","url":"/area/computer-code"},{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Medical","url":"/area/medical"},{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":296,"papers_with_code":169,"benchmarks":9,"benchmark_tables_in_archive":10,"benchmark_tables_shown":9,"benchmark_tables_withheld_as_spam":1,"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":8,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on","slug":"weakly-supervised-semantic-segmentation-on","dataset":"PASCAL VOC 2012 val","dataset_url":null,"rows_in_archive":73,"metrics":["Mean IoU"],"first_row_in_archive_order":{"model":"SemPLeS (Swin-L)","paper_title":"Semantic Prompt Learning for Weakly-Supervised Semantic Segmentation","paper_url":"/paper/semples-semantic-prompt-learning-for-weakly","paper_date":"2024-01-22","arxiv_id":"2401.11791","code_links":[{"title":"nvlabs/semples","url":"https://github.com/nvlabs/semples"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-1","slug":"weakly-supervised-semantic-segmentation-on-1","dataset":"PASCAL VOC 2012 test","dataset_url":"/dataset/pascal-voc-2012-test","rows_in_archive":60,"metrics":["Mean IoU"],"first_row_in_archive_order":{"model":"SemPLeS (Swin-L)","paper_title":"Semantic Prompt Learning for Weakly-Supervised Semantic Segmentation","paper_url":"/paper/semples-semantic-prompt-learning-for-weakly","paper_date":"2024-01-22","arxiv_id":"2401.11791","code_links":[{"title":"nvlabs/semples","url":"https://github.com/nvlabs/semples"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-4","slug":"weakly-supervised-semantic-segmentation-on-4","dataset":"COCO 2014 val","dataset_url":null,"rows_in_archive":39,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"DHR (Swin-L, Mask2Former)","paper_title":"DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions for Weakly-Supervised Semantic Segmentation","paper_url":"/paper/dhr-dual-features-driven-hierarchical","paper_date":"2024-03-30","arxiv_id":"2404.00380","code_links":[{"title":"shjo-april/DHR","url":"https://github.com/shjo-april/DHR"}],"syntology":{"n":9,"n_ran":9,"n_unverified":0,"n_pointer_only":9}}},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-14","slug":"weakly-supervised-semantic-segmentation-on-14","dataset":"PASCAL VOC 2012 train","dataset_url":null,"rows_in_archive":4,"metrics":["Mean IoU"],"first_row_in_archive_order":{"model":"FMA-WSSS","paper_title":"Foundation Model Assisted Weakly Supervised Semantic Segmentation","paper_url":"/paper/foundation-model-assisted-weakly-supervised","paper_date":"2023-12-06","arxiv_id":"2312.03585","code_links":[{"title":"HAL-42/FMA-WSSS","url":"https://github.com/HAL-42/FMA-WSSS"}],"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-16","slug":"weakly-supervised-semantic-segmentation-on-16","dataset":"Cityscapes val","dataset_url":"/dataset/cityscapes","rows_in_archive":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"CARB","paper_title":"Weakly Supervised Semantic Segmentation for Driving Scenes","paper_url":"/paper/weakly-supervised-semantic-segmentation-for-1","paper_date":"2023-12-21","arxiv_id":"2312.13646","code_links":[{"title":"k0u-id/carb","url":"https://github.com/k0u-id/carb"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-17","slug":"weakly-supervised-semantic-segmentation-on-17","dataset":"Cityscapes test","dataset_url":"/dataset/cityscapes","rows_in_archive":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"CARB","paper_title":"Weakly Supervised Semantic Segmentation for Driving Scenes","paper_url":"/paper/weakly-supervised-semantic-segmentation-for-1","paper_date":"2023-12-21","arxiv_id":"2312.13646","code_links":[{"title":"k0u-id/carb","url":"https://github.com/k0u-id/carb"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-20","slug":"weakly-supervised-semantic-segmentation-on-20","dataset":"ADE20K val","dataset_url":"/dataset/ade20k","rows_in_archive":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"DHR (Swin-L, Mask2Former)","paper_title":"DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions for Weakly-Supervised Semantic Segmentation","paper_url":"/paper/dhr-dual-features-driven-hierarchical","paper_date":"2024-03-30","arxiv_id":"2404.00380","code_links":[{"title":"shjo-april/DHR","url":"https://github.com/shjo-april/DHR"}],"syntology":{"n":9,"n_ran":9,"n_unverified":0,"n_pointer_only":9}}},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-21","slug":"weakly-supervised-semantic-segmentation-on-21","dataset":"COCO-Stuff val","dataset_url":null,"rows_in_archive":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"DHR (Swin-L, Mask2Former)","paper_title":"DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions for Weakly-Supervised Semantic Segmentation","paper_url":"/paper/dhr-dual-features-driven-hierarchical","paper_date":"2024-03-30","arxiv_id":"2404.00380","code_links":[{"title":"shjo-april/DHR","url":"https://github.com/shjo-april/DHR"}],"syntology":{"n":9,"n_ran":9,"n_unverified":0,"n_pointer_only":9}}},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-22","slug":"weakly-supervised-semantic-segmentation-on-22","dataset":"PASCAL Context val","dataset_url":null,"rows_in_archive":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"DHR (Swin-L, Mask2Former)","paper_title":"DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions for Weakly-Supervised Semantic Segmentation","paper_url":"/paper/dhr-dual-features-driven-hierarchical","paper_date":"2024-03-30","arxiv_id":"2404.00380","code_links":[{"title":"shjo-april/DHR","url":"https://github.com/shjo-april/DHR"}],"syntology":{"n":9,"n_ran":9,"n_unverified":0,"n_pointer_only":9}}}],"datasets":[{"url":"/dataset/cityscapes","name":"Cityscapes","full_name":"","num_papers_in_archive":3702},{"url":"/dataset/ade20k","name":"ADE20K","full_name":"","num_papers_in_archive":1213},{"url":"/dataset/pascal-voc-2012-test","name":"PASCAL VOC 2012 test","full_name":"","num_papers_in_archive":116},{"url":"/dataset/sen12ms","name":"SEN12MS","full_name":"","num_papers_in_archive":34},{"url":"/dataset/scribblesup","name":"ScribbleSup","full_name":"PASCAL-Scribble Dataset","num_papers_in_archive":26},{"url":"/dataset/scribblekitti","name":"ScribbleKITTI","full_name":"","num_papers_in_archive":19},{"url":"/dataset/acdc-scribbles","name":"ACDC Scribbles","full_name":"","num_papers_in_archive":10},{"url":"/dataset/chexlocalize","name":"CheXlocalize","full_name":"","num_papers_in_archive":3}],"subtasks":[],"parent_tasks":[{"url":"/task/semantic-segmentation","name":"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":169,"tagged_in_all":296,"items":[{"url":"/paper/weakly-supervised-learning-of-instance","title":"Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations","date":"2019-04-10","arxiv_id":"1904.05044","repositories_listed":8,"syntology":{"n":10,"n_ran":1,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/weakly-supervised-semantic-segmentation-for-2","title":"Weakly Supervised Semantic Segmentation for Large-Scale Point Cloud","date":"2022-12-09","arxiv_id":"2212.04744","repositories_listed":4,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/puzzle-cam-improved-localization-via-matching","title":"Puzzle-CAM: Improved localization via matching partial and full features","date":"2021-01-27","arxiv_id":"2101.11253","repositories_listed":4,"syntology":null},{"url":"/paper/constrained-cnn-losses-for-weakly-supervised","title":"Constrained-CNN losses for weakly supervised segmentation","date":"2018-05-12","arxiv_id":"1805.04628","repositories_listed":4,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/learning-without-exact-guidance-updating","title":"Learning without Exact Guidance: Updating Large-scale High-resolution Land Cover Maps from Low-resolution Historical Labels","date":"2024-03-05","arxiv_id":"2403.02746","repositories_listed":3,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/weakly-and-semi-supervised-learning-of-a-dcnn","title":"Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation","date":"2015-02-09","arxiv_id":"1502.02734","repositories_listed":3,"syntology":null},{"url":"/paper/exploiting-inherent-class-label-towards","title":"Exploiting Inherent Class Label: Towards Robust Scribble Supervised Semantic Segmentation","date":"2025-03-18","arxiv_id":"2503.13895","repositories_listed":2,"syntology":null},{"url":"/paper/enhanced-prompt-leveraged-weakly-supervised","title":"EP-SAM: Weakly Supervised Histopathology Segmentation via Enhanced Prompt with Segment Anything","date":"2024-10-17","arxiv_id":"2410.13621","repositories_listed":2,"syntology":null},{"url":"/paper/background-activation-suppression-for-weakly-1","title":"Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation","date":"2023-09-22","arxiv_id":"2309.12943","repositories_listed":2,"syntology":null},{"url":"/paper/prompting-classes-exploring-the-power-of","title":"Prompting classes: Exploring the Power of Prompt Class Learning in Weakly Supervised Semantic Segmentation","date":"2023-06-30","arxiv_id":"2307.00097","repositories_listed":2,"syntology":null},{"url":"/paper/boundarycam-a-boundary-based-refinement","title":"ReFit: A Framework for Refinement of Weakly Supervised Semantic Segmentation using Object Border Fitting for Medical Images","date":"2023-03-14","arxiv_id":"2303.07853","repositories_listed":2,"syntology":null},{"url":"/paper/recurseed-and-certainmix-for-weakly","title":"RecurSeed and EdgePredictMix: Pseudo-Label Refinement Learning for Weakly Supervised Semantic Segmentation across Single- and Multi-Stage Frameworks","date":"2022-04-14","arxiv_id":"2204.06754","repositories_listed":2,"syntology":null},{"url":"/paper/learning-affinity-from-attention-end-to-end","title":"Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers","date":"2022-03-05","arxiv_id":"2203.02664","repositories_listed":2,"syntology":null},{"url":"/paper/cross-language-image-matching-for-weakly","title":"Cross Language Image Matching for Weakly Supervised Semantic Segmentation","date":"2022-03-05","arxiv_id":"2203.02668","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/adaptive-early-learning-correction-for","title":"Adaptive Early-Learning Correction for Segmentation from Noisy Annotations","date":"2021-10-07","arxiv_id":"2110.03740","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":1}},{"url":"/paper/pseudo-mask-matters-inweakly-supervised","title":"Pseudo-mask Matters in Weakly-supervised Semantic Segmentation","date":"2021-08-30","arxiv_id":"2108.12995","repositories_listed":2,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/sqn-weakly-supervised-semantic-segmentation","title":"SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds","date":"2021-04-11","arxiv_id":"2104.04891","repositories_listed":2,"syntology":null},{"url":"/paper/background-aware-pooling-and-noise-aware-loss","title":"Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation","date":"2021-04-02","arxiv_id":"2104.00905","repositories_listed":2,"syntology":null},{"url":"/paper/learning-whole-slide-segmentation-from","title":"Learning Whole-Slide Segmentation from Inexact and Incomplete Labels using Tissue Graphs","date":"2021-03-04","arxiv_id":"2103.03129","repositories_listed":2,"syntology":null},{"url":"/paper/mining-cross-image-semantics-for-weakly","title":"Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation","date":"2020-07-03","arxiv_id":"2007.01947","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/self-supervised-equivariant-attention","title":"Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation","date":"2020-04-09","arxiv_id":"2004.04581","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/integral-object-mining-via-online-attention","title":"Integral Object Mining via Online Attention Accumulation","date":"2019-10-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/learning-pixel-level-semantic-affinity-with","title":"Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation","date":"2018-03-28","arxiv_id":"1803.10464","repositories_listed":2,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/discovering-class-specific-pixels-for-weakly","title":"Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation","date":"2017-07-18","arxiv_id":"1707.05821","repositories_listed":2,"syntology":null},{"url":"/paper/spars-self-play-adversarial-reinforcement","title":"SPARS: Self-Play Adversarial Reinforcement Learning for Segmentation of Liver Tumours","date":"2025-05-25","arxiv_id":"2505.18989","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-clip-s-dense-knowledge-for-weakly","title":"Exploring CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation","date":"2025-03-26","arxiv_id":"2503.20826","repositories_listed":1,"syntology":{"n":11,"n_ran":4,"n_unverified":7,"n_pointer_only":11}},{"url":"/paper/doei-dual-optimization-of-embedding","title":"DOEI: Dual Optimization of Embedding Information for Attention-Enhanced Class Activation Maps","date":"2025-02-21","arxiv_id":"2502.15885","repositories_listed":1,"syntology":null},{"url":"/paper/pot-prototypical-optimal-transport-for-weakly","title":"POT: Prototypical Optimal Transport for Weakly Supervised Semantic Segmentation","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ffr-frequency-feature-rectification-for","title":"FFR: Frequency Feature Rectification for Weakly Supervised Semantic Segmentation","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hisynseg-weakly-supervised-histopathological","title":"HisynSeg: Weakly-Supervised Histopathological Image Segmentation via Image-Mixing Synthesis and Consistency Regularization","date":"2024-12-30","arxiv_id":"2412.20924","repositories_listed":1,"syntology":null}],"syntology_records":11,"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"}}