{"url":"/task/weakly-supervised-object-detection","name":"Weakly Supervised Object Detection","slug":"weakly-supervised-object-detection","description_markdown":"Weakly Supervised Object Detection (WSOD) is the task of training object detectors with only image tag supervisions.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Soft Proposal Networks for Weakly Supervised Object Localization](https://arxiv.org/pdf/1709.01829v1.pdf) )</span>","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":142,"papers_with_code":58,"benchmarks":17,"benchmark_tables_in_archive":17,"benchmark_tables_shown":17,"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":14,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/weakly-supervised-object-detection-on-pascal-1","slug":"weakly-supervised-object-detection-on-pascal-1","dataset":"PASCAL VOC 2007","dataset_url":"/dataset/pascal-voc-2007","rows_in_archive":41,"metrics":["MAP"],"first_row_in_archive_order":{"model":"WeakSAM-MIST-DINO (with SAM)","paper_title":"WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition","paper_url":"/paper/weaksam-segment-anything-meets-weakly","paper_date":"2024-02-22","arxiv_id":"2402.14812","code_links":[{"title":"hustvl/weaksam","url":"https://github.com/hustvl/weaksam"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-object-detection-on-pascal","slug":"weakly-supervised-object-detection-on-pascal","dataset":"PASCAL VOC 2012 test","dataset_url":"/dataset/pascal-voc-2012-test","rows_in_archive":32,"metrics":["MAP"],"first_row_in_archive_order":{"model":"WeakSAM-MIST-DINO (with SAM)","paper_title":"WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition","paper_url":"/paper/weaksam-segment-anything-meets-weakly","paper_date":"2024-02-22","arxiv_id":"2402.14812","code_links":[{"title":"hustvl/weaksam","url":"https://github.com/hustvl/weaksam"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-object-detection-on-1","slug":"weakly-supervised-object-detection-on-1","dataset":"Watercolor2k","dataset_url":"/dataset/watercolor2k","rows_in_archive":12,"metrics":["MAP"],"first_row_in_archive_order":{"model":"TADP","paper_title":"Text-image Alignment for Diffusion-based Perception","paper_url":"/paper/text-image-alignment-for-diffusion-based","paper_date":"2023-09-29","arxiv_id":"2310.00031","code_links":[{"title":"damaggu/tadp","url":"https://github.com/damaggu/tadp"},{"title":"nkondapa/RSVC","url":"https://github.com/nkondapa/RSVC"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-object-detection-on-comic2k","slug":"weakly-supervised-object-detection-on-comic2k","dataset":"Comic2k","dataset_url":"/dataset/comic2k","rows_in_archive":8,"metrics":["MAP"],"first_row_in_archive_order":{"model":"DASS-Detector (YOLOX Tiny)","paper_title":"Domain-Adaptive Self-Supervised Pre-Training for Face & Body Detection in Drawings","paper_url":"/paper/domain-adaptive-self-supervised-pre-training","paper_date":"2022-11-19","arxiv_id":"2211.10641","code_links":[{"title":"barisbatuhan/dass_det_inference","url":"https://github.com/barisbatuhan/dass_det_inference"},{"title":"barisbatuhan/dass_detector","url":"https://github.com/barisbatuhan/dass_detector"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-object-detection-on-2","slug":"weakly-supervised-object-detection-on-2","dataset":"Clipart1k","dataset_url":"/dataset/clipart1k","rows_in_archive":7,"metrics":["MAP"],"first_row_in_archive_order":{"model":"H2FA R-CNN (clipart_all)","paper_title":"H2FA R-CNN: Holistic and Hierarchical Feature Alignment for Cross-Domain Weakly Supervised Object Detection","paper_url":"/paper/h2fa-r-cnn-holistic-and-hierarchical-feature","paper_date":"2022-01-01","arxiv_id":null,"code_links":[{"title":"xuyunqiu/h2fa_r-cnn","url":"https://github.com/xuyunqiu/h2fa_r-cnn"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-object-detection-on-ms-coco","slug":"weakly-supervised-object-detection-on-ms-coco","dataset":"MS-COCO-2014","dataset_url":null,"rows_in_archive":7,"metrics":["AP"],"first_row_in_archive_order":{"model":"WeakSAM-MIST-DINO (with SAM)","paper_title":"WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition","paper_url":"/paper/weaksam-segment-anything-meets-weakly","paper_date":"2024-02-22","arxiv_id":"2402.14812","code_links":[{"title":"hustvl/weaksam","url":"https://github.com/hustvl/weaksam"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-object-detection-on-4","slug":"weakly-supervised-object-detection-on-4","dataset":"Charades","dataset_url":"/dataset/charades","rows_in_archive":6,"metrics":["MAP"],"first_row_in_archive_order":{"model":"Spatial Prior","paper_title":"Activity Driven Weakly Supervised Object Detection","paper_url":"/paper/activity-driven-weakly-supervised-object","paper_date":"2019-04-02","arxiv_id":"1904.01665","code_links":[],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-object-detection-on-coco","slug":"weakly-supervised-object-detection-on-coco","dataset":"COCO (Common Objects in Context)","dataset_url":"/dataset/coco","rows_in_archive":5,"metrics":["MAP"],"first_row_in_archive_order":{"model":"MSLPD","paper_title":"Few-Example Object Detection with Model Communication","paper_url":"/paper/few-example-object-detection-with-model","paper_date":"2017-06-26","arxiv_id":"1706.08249","code_links":[{"title":"D-X-Y/DXY-Projects","url":"https://github.com/D-X-Y/DXY-Projects/tree/master/MSPLD"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-object-detection-on","slug":"weakly-supervised-object-detection-on","dataset":"ImageNet","dataset_url":"/dataset/imagenet","rows_in_archive":4,"metrics":["MAP"],"first_row_in_archive_order":{"model":"PCL-OB-G-Ens + FRCNN","paper_title":"PCL: Proposal Cluster Learning for Weakly Supervised Object Detection","paper_url":"/paper/pcl-proposal-cluster-learning-for-weakly","paper_date":"2018-07-09","arxiv_id":"1807.03342","code_links":[{"title":"ppengtang/pcl.pytorch","url":"https://github.com/ppengtang/pcl.pytorch"},{"title":"ppengtang/oicr","url":"https://github.com/ppengtang/oicr"},{"title":"JoegameZhou/mPanGu-Alpha-53","url":"https://github.com/JoegameZhou/mPanGu-Alpha-53"},{"title":"George-Holbrow-Wilshaw/Human-Protein-Atlas-Kaggle","url":"https://github.com/George-Holbrow-Wilshaw/Human-Protein-Atlas-Kaggle"}],"syntology":{"n":7,"n_ran":1,"n_unverified":6,"n_pointer_only":0}}},{"leaderboard":"/sota/weakly-supervised-object-detection-on-coco-2","slug":"weakly-supervised-object-detection-on-coco-2","dataset":"COCO test-dev","dataset_url":"/dataset/coco","rows_in_archive":4,"metrics":["AP50"],"first_row_in_archive_order":{"model":"wetectron(single-model, VGG16)","paper_title":"Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection","paper_url":"/paper/instance-aware-context-focused-and-memory","paper_date":"2020-04-09","arxiv_id":"2004.04725","code_links":[{"title":"NVlabs/wetectron","url":"https://github.com/NVlabs/wetectron"},{"title":"ppengtang/pcl.pytorch","url":"https://github.com/ppengtang/pcl.pytorch"}],"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/weakly-supervised-object-detection-on-hico","slug":"weakly-supervised-object-detection-on-hico","dataset":"HICO-DET","dataset_url":"/dataset/hico-det","rows_in_archive":4,"metrics":["MAP"],"first_row_in_archive_order":{"model":"Spatial Prior","paper_title":"Activity Driven Weakly Supervised Object Detection","paper_url":"/paper/activity-driven-weakly-supervised-object","paper_date":"2019-04-02","arxiv_id":"1904.01665","code_links":[],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-object-detection-on-3","slug":"weakly-supervised-object-detection-on-3","dataset":"PeopleArt","dataset_url":"/dataset/peopleart","rows_in_archive":2,"metrics":["MAP"],"first_row_in_archive_order":{"model":"Polyhedral MI-max","paper_title":"Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts","paper_url":"/paper/multiple-instance-learning-on-deep-features","paper_date":"2020-08-03","arxiv_id":"2008.01178","code_links":[{"title":"ngonthier/Mi_max","url":"https://github.com/ngonthier/Mi_max"},{"title":"nicaogr/Mi_max","url":"https://github.com/nicaogr/Mi_max"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-object-detection-on-6","slug":"weakly-supervised-object-detection-on-6","dataset":"Cityscapes-to-Foggy Cityscapes","dataset_url":"/dataset/foggy-cityscapes","rows_in_archive":2,"metrics":["mAP"],"first_row_in_archive_order":{"model":"MEAA","paper_title":"Domain-Adaptive Object Detection via Uncertainty-Aware Distribution Alignment","paper_url":"/paper/domain-adaptive-object-detection-via-1","paper_date":"2020-10-31","arxiv_id":null,"code_links":[{"title":"basiclab/DA-OD-MEAA-PyTorch","url":"https://github.com/basiclab/DA-OD-MEAA-PyTorch"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-object-detection-on-iconart","slug":"weakly-supervised-object-detection-on-iconart","dataset":"IconArt","dataset_url":"/dataset/iconart","rows_in_archive":2,"metrics":["MAP"],"first_row_in_archive_order":{"model":"MI_Net [wang_revisiting_2018]","paper_title":"Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts","paper_url":"/paper/multiple-instance-learning-on-deep-features","paper_date":"2020-08-03","arxiv_id":"2008.01178","code_links":[{"title":"ngonthier/Mi_max","url":"https://github.com/ngonthier/Mi_max"},{"title":"nicaogr/Mi_max","url":"https://github.com/nicaogr/Mi_max"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-object-detection-on-5","slug":"weakly-supervised-object-detection-on-5","dataset":"CASPAPaintings","dataset_url":null,"rows_in_archive":1,"metrics":["Mean mAP"],"first_row_in_archive_order":{"model":"MI-max","paper_title":"Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts","paper_url":"/paper/multiple-instance-learning-on-deep-features","paper_date":"2020-08-03","arxiv_id":"2008.01178","code_links":[{"title":"ngonthier/Mi_max","url":"https://github.com/ngonthier/Mi_max"},{"title":"nicaogr/Mi_max","url":"https://github.com/nicaogr/Mi_max"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-object-detection-on-ms-coco-1","slug":"weakly-supervised-object-detection-on-ms-coco-1","dataset":"MS-COCO-2017","dataset_url":null,"rows_in_archive":1,"metrics":["AP"],"first_row_in_archive_order":{"model":"OD-WSCL","paper_title":"Object Discovery via Contrastive Learning for Weakly Supervised Object Detection","paper_url":"/paper/object-discovery-via-contrastive-learning-for","paper_date":"2022-08-16","arxiv_id":"2208.07576","code_links":[{"title":"jinhseo/od-wscl","url":"https://github.com/jinhseo/od-wscl"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-object-detection-on-mscoco","slug":"weakly-supervised-object-detection-on-mscoco","dataset":"MSCOCO","dataset_url":"/dataset/mscoco","rows_in_archive":1,"metrics":["mAP","mAP@50"],"first_row_in_archive_order":{"model":"CASD(ResNet50)","paper_title":"Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection","paper_url":"/paper/comprehensive-attention-self-distillation-for","paper_date":"2020-10-22","arxiv_id":"2010.12023","code_links":[{"title":"DeLightCMU/CASD","url":"https://github.com/DeLightCMU/CASD"}],"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":6}}}],"datasets":[{"url":"/dataset/imagenet","name":"ImageNet","full_name":"","num_papers_in_archive":15430},{"url":"/dataset/coco","name":"COCO (Common Objects in Context)","full_name":"Common Objects in Context","num_papers_in_archive":11922},{"url":"/dataset/charades","name":"Charades","full_name":"","num_papers_in_archive":428},{"url":"/dataset/foggy-cityscapes","name":"Foggy Cityscapes","full_name":"","num_papers_in_archive":249},{"url":"/dataset/hico-det","name":"HICO-DET","full_name":"HICO-DET","num_papers_in_archive":180},{"url":"/dataset/pascal-voc-2007","name":"PASCAL VOC 2007","full_name":"PASCAL VOC 2007","num_papers_in_archive":126},{"url":"/dataset/pascal-voc-2012-test","name":"PASCAL VOC 2012 test","full_name":"","num_papers_in_archive":116},{"url":"/dataset/mscoco","name":"MSCOCO","full_name":"","num_papers_in_archive":90},{"url":"/dataset/clipart1k","name":"Clipart1k","full_name":"","num_papers_in_archive":48},{"url":"/dataset/watercolor2k","name":"Watercolor2k","full_name":"","num_papers_in_archive":37},{"url":"/dataset/comic2k","name":"Comic2k","full_name":"","num_papers_in_archive":29},{"url":"/dataset/peopleart","name":"PeopleArt","full_name":"PeopleArt","num_papers_in_archive":12},{"url":"/dataset/iconart","name":"IconArt","full_name":"","num_papers_in_archive":7},{"url":"/dataset/leukemiaattri","name":"LeukemiaAttri","full_name":"","num_papers_in_archive":2}],"subtasks":[],"parent_tasks":[{"url":"/task/object-detection","name":"Object Detection"}],"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":58,"tagged_in_all":142,"items":[{"url":"/paper/weakly-supervised-deep-detection-networks","title":"Weakly Supervised Deep Detection Networks","date":"2015-11-09","arxiv_id":"1511.02853","repositories_listed":5,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":1}},{"url":"/paper/pcl-proposal-cluster-learning-for-weakly","title":"PCL: Proposal Cluster Learning for Weakly Supervised Object Detection","date":"2018-07-09","arxiv_id":"1807.03342","repositories_listed":4,"syntology":{"n":7,"n_ran":1,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/multiple-instance-detection-network-with","title":"Multiple Instance Detection Network with Online Instance Classifier Refinement","date":"2017-04-01","arxiv_id":"1704.00138","repositories_listed":4,"syntology":null},{"url":"/paper/cross-domain-weakly-supervised-object","title":"Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation","date":"2018-03-30","arxiv_id":"1803.11365","repositories_listed":3,"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/text-image-alignment-for-diffusion-based","title":"Text-image Alignment for Diffusion-based Perception","date":"2023-09-29","arxiv_id":"2310.00031","repositories_listed":2,"syntology":null},{"url":"/paper/domain-adaptive-self-supervised-pre-training","title":"Domain-Adaptive Self-Supervised Pre-Training for Face & Body Detection in Drawings","date":"2022-11-19","arxiv_id":"2211.10641","repositories_listed":2,"syntology":null},{"url":"/paper/multiple-instance-learning-on-deep-features","title":"Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts","date":"2020-08-03","arxiv_id":"2008.01178","repositories_listed":2,"syntology":null},{"url":"/paper/instance-aware-context-focused-and-memory","title":"Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection","date":"2020-04-09","arxiv_id":"2004.04725","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/weakly-supervised-object-detection-in","title":"Weakly Supervised Object Detection in Artworks","date":"2018-10-05","arxiv_id":"1810.02569","repositories_listed":2,"syntology":null},{"url":"/paper/wildcat-weakly-supervised-learning-of-deep","title":"WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation","date":"2017-07-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/weakly-supervised-object-detection-for","title":"Weakly Supervised Object Detection for Automatic Tooth-marked Tongue Recognition","date":"2024-08-29","arxiv_id":"2408.16451","repositories_listed":1,"syntology":null},{"url":"/paper/disentangling-spatio-temporal-knowledge-for","title":"Disentangling spatio-temporal knowledge for weakly supervised object detection and segmentation in surgical video","date":"2024-07-22","arxiv_id":"2407.15794","repositories_listed":1,"syntology":null},{"url":"/paper/huwsod-holistic-self-training-for-unified","title":"HUWSOD: Holistic Self-training for Unified Weakly Supervised Object Detection","date":"2024-06-27","arxiv_id":"2406.19394","repositories_listed":1,"syntology":null},{"url":"/paper/smart-feature-is-what-you-need","title":"Smart Feature is What You Need","date":"2024-06-22","arxiv_id":"2406.15805","repositories_listed":1,"syntology":null},{"url":"/paper/sparse-generation-making-pseudo-labels-sparse","title":"Sparse Generation: Making Pseudo Labels Sparse for Point Weakly Supervised Object Detection on Low Data Volume","date":"2024-03-28","arxiv_id":"2403.19306","repositories_listed":1,"syntology":null},{"url":"/paper/weaksam-segment-anything-meets-weakly","title":"WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition","date":"2024-02-22","arxiv_id":"2402.14812","repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-object-detection-in-chest-x","title":"Weakly Supervised Object Detection in Chest X-Rays with Differentiable ROI Proposal Networks and Soft ROI Pooling","date":"2024-02-19","arxiv_id":"2402.11985","repositories_listed":1,"syntology":null},{"url":"/paper/leod-label-efficient-object-detection-for","title":"LEOD: Label-Efficient Object Detection for Event Cameras","date":"2023-11-29","arxiv_id":"2311.17286","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/identifying-light-curve-signals-with-a-deep","title":"Identifying Light-curve Signals with a Deep Learning Based Object Detection Algorithm. II. A General Light Curve Classification Framework","date":"2023-11-14","arxiv_id":"2311.08080","repositories_listed":1,"syntology":null},{"url":"/paper/a-weakly-supervised-learning-method-for-cell","title":"A Weakly Supervised Learning Method for Cell Detection and Tracking Using Incomplete Initial Annotations","date":"2023-11-07","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/alwod-active-learning-for-weakly-supervised","title":"ALWOD: Active Learning for Weakly-Supervised Object Detection","date":"2023-09-14","arxiv_id":"2309.07914","repositories_listed":1,"syntology":null},{"url":"/paper/gall-bladder-cancer-detection-from-us-images","title":"Gall Bladder Cancer Detection from US Images with Only Image Level Labels","date":"2023-09-11","arxiv_id":"2309.05261","repositories_listed":1,"syntology":null},{"url":"/paper/anatomy-driven-pathology-detection-on-chest-x","title":"Anatomy-Driven Pathology Detection on Chest X-rays","date":"2023-09-05","arxiv_id":"2309.02578","repositories_listed":1,"syntology":null},{"url":"/paper/pdl-regularizing-multiple-instance-learning","title":"PDL: Regularizing Multiple Instance Learning with Progressive Dropout Layers","date":"2023-08-19","arxiv_id":"2308.10112","repositories_listed":1,"syntology":null},{"url":"/paper/cyclic-bootstrap-labeling-for-weakly","title":"Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection","date":"2023-08-11","arxiv_id":"2308.05991","repositories_listed":1,"syntology":null},{"url":"/paper/max-pooling-with-vision-transformers","title":"Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation","date":"2022-10-31","arxiv_id":"2210.17400","repositories_listed":1,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/imaginarynet-learning-object-detectors","title":"ImaginaryNet: Learning Object Detectors without Real Images and Annotations","date":"2022-10-13","arxiv_id":"2210.06886","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/object-discovery-via-contrastive-learning-for","title":"Object Discovery via Contrastive Learning for Weakly Supervised Object Detection","date":"2022-08-16","arxiv_id":"2208.07576","repositories_listed":1,"syntology":null},{"url":"/paper/active-learning-strategies-for-weakly","title":"Active Learning Strategies for Weakly-supervised Object Detection","date":"2022-07-25","arxiv_id":"2207.12112","repositories_listed":1,"syntology":null},{"url":"/paper/w2n-switching-from-weak-supervision-to-noisy","title":"W2N:Switching From Weak Supervision to Noisy Supervision for Object Detection","date":"2022-07-25","arxiv_id":"2207.12104","repositories_listed":1,"syntology":null}],"syntology_records":7,"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"}}