{"url":"/sota/weakly-supervised-object-detection-on-pascal","task":{"name":"Weakly Supervised Object Detection","url":"/task/weakly-supervised-object-detection","note":null},"dataset":{"name":"PASCAL VOC 2012 test","url":"/dataset/pascal-voc-2012-test"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"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>","description_from":"task","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":["MAP"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"MAP":"higher"}},"counts":{"rows":32,"rows_with_code":19,"rows_with_paper_page":32,"rows_dated":32,"rows_using_additional_data":2},"rows":[{"rank_in_archive_order":1,"model":"WeakSAM-MIST-DINO (with SAM)","metrics":{"MAP":"70.2"},"uses_additional_data":false,"paper_date":"2024-02-22","paper":"/paper/weaksam-segment-anything-meets-weakly","paper_url":"https://arxiv.org/abs/2402.14812v2","paper_title":"WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition","code":"https://github.com/hustvl/weaksam","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"WeakSAM-MIST-Faster RCNN (with SAM)","metrics":{"MAP":"69.2"},"uses_additional_data":false,"paper_date":"2024-02-22","paper":"/paper/weaksam-segment-anything-meets-weakly","paper_url":"https://arxiv.org/abs/2402.14812v2","paper_title":"WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition","code":"https://github.com/hustvl/weaksam","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"WeakSAM-MIST (with SAM)","metrics":{"MAP":"66.9"},"uses_additional_data":false,"paper_date":"2024-02-22","paper":"/paper/weaksam-segment-anything-meets-weakly","paper_url":"https://arxiv.org/abs/2402.14812v2","paper_title":"WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition","code":"https://github.com/hustvl/weaksam","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"WeakSAM-OICR-DINO (with SAM)","metrics":{"MAP":"63.7"},"uses_additional_data":false,"paper_date":"2024-02-22","paper":"/paper/weaksam-segment-anything-meets-weakly","paper_url":"https://arxiv.org/abs/2402.14812v2","paper_title":"WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition","code":"https://github.com/hustvl/weaksam","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"WeakSAM-OICR-Faster RCNN (with SAM)","metrics":{"MAP":"62.9"},"uses_additional_data":false,"paper_date":"2024-02-22","paper":"/paper/weaksam-segment-anything-meets-weakly","paper_url":"https://arxiv.org/abs/2402.14812v2","paper_title":"WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition","code":"https://github.com/hustvl/weaksam","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"WeakSAM-OICR (with SAM)","metrics":{"MAP":"58.4"},"uses_additional_data":false,"paper_date":"2024-02-22","paper":"/paper/weaksam-segment-anything-meets-weakly","paper_url":"https://arxiv.org/abs/2402.14812v2","paper_title":"WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition","code":"https://github.com/hustvl/weaksam","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"OD-WSCL","metrics":{"MAP":"54.6"},"uses_additional_data":false,"paper_date":"2022-08-16","paper":"/paper/object-discovery-via-contrastive-learning-for","paper_url":"https://arxiv.org/abs/2208.07576v2","paper_title":"Object Discovery via Contrastive Learning for Weakly Supervised Object Detection","code":"https://github.com/jinhseo/od-wscl","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"CASD(VGG16)","metrics":{"MAP":"53.6"},"uses_additional_data":false,"paper_date":"2020-10-22","paper":"/paper/comprehensive-attention-self-distillation-for","paper_url":"https://arxiv.org/abs/2010.12023v1","paper_title":"Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection","code":"https://github.com/DeLightCMU/CASD","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":9,"model":"wetectron(single-model)","metrics":{"MAP":"52.1"},"uses_additional_data":false,"paper_date":"2020-04-09","paper":"/paper/instance-aware-context-focused-and-memory","paper_url":"https://arxiv.org/abs/2004.04725v3","paper_title":"Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection","code":"https://github.com/NVlabs/wetectron","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"C-MIDN+FRCNN","metrics":{"MAP":"50.3"},"uses_additional_data":false,"paper_date":"2019-10-01","paper":"/paper/c-midn-coupled-multiple-instance-detection","paper_url":"http://openaccess.thecvf.com/content_ICCV_2019/html/Gao_C-MIDN_Coupled_Multiple_Instance_Detection_Network_With_Segmentation_Guidance_for_ICCV_2019_paper.html","paper_title":"C-MIDN: Coupled Multiple Instance Detection Network With Segmentation Guidance for Weakly Supervised Object Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"Pred Net (Ens)","metrics":{"MAP":"49.5"},"uses_additional_data":false,"paper_date":"2018-11-25","paper":"/paper/dissimilarity-coefficient-based-weakly","paper_url":"http://arxiv.org/abs/1811.10016v1","paper_title":"Dissimilarity Coefficient based Weakly Supervised Object Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"Our-Ens","metrics":{"MAP":"49.5"},"uses_additional_data":false,"paper_date":"2019-11-27","paper":"/paper/towards-precise-end-to-end-weakly-supervised-1","paper_url":"https://arxiv.org/abs/1911.12148v1","paper_title":"Towards Precise End-to-end Weakly Supervised Object Detection Network","code":"https://github.com/ppengtang/pcl.pytorch","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"Ours + FRCNN","metrics":{"MAP":"48.1"},"uses_additional_data":false,"paper_date":"2019-08-10","paper":"/paper/object-aware-instance-labeling-for-weakly","paper_url":"https://arxiv.org/abs/1908.03792v1","paper_title":"Object-Aware Instance Labeling for Weakly Supervised Object Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"Ours+FRCNN","metrics":{"MAP":"48.0"},"uses_additional_data":false,"paper_date":"2019-06-14","paper":"/paper/utilizing-the-instability-in-weakly","paper_url":"https://arxiv.org/abs/1906.06023v1","paper_title":"Utilizing the Instability in Weakly Supervised Object Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"WSD+PGE+PGA+FSD2","metrics":{"MAP":"47.8"},"uses_additional_data":false,"paper_date":"2018-06-01","paper":"/paper/w2f-a-weakly-supervised-to-fully-supervised","paper_url":"http://openaccess.thecvf.com/content_cvpr_2018/html/Zhang_W2F_A_Weakly-Supervised_CVPR_2018_paper.html","paper_title":"W2F: A Weakly-Supervised to Fully-Supervised Framework for Object Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"WSOD2","metrics":{"MAP":"47.2"},"uses_additional_data":false,"paper_date":"2019-09-11","paper":"/paper/wsod2-learning-bottom-up-and-top-down","paper_url":"https://arxiv.org/abs/1909.04972","paper_title":"WSOD2: Learning Bottom-up and Top-down Objectness Distillation forWeakly-supervised Object Detection","code":null,"n_code_links":0,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":17,"model":"C-MIL","metrics":{"MAP":"46.7"},"uses_additional_data":false,"paper_date":"2019-04-11","paper":"/paper/c-mil-continuation-multiple-instance-learning","paper_url":"http://arxiv.org/abs/1904.05647v1","paper_title":"C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection","code":"https://github.com/Winfrand/C-MIL","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"OIM+IR+FRCNN","metrics":{"MAP":"46.4"},"uses_additional_data":false,"paper_date":"2020-02-04","paper":"/paper/object-instance-mining-for-weakly-supervised","paper_url":"https://arxiv.org/abs/2002.01087v1","paper_title":"Object Instance Mining for Weakly Supervised Object Detection","code":"https://github.com/bigvideoresearch/OIM","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"WS-JDS FRCNN","metrics":{"MAP":"46.1"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/cyclic-guidance-for-weakly-supervised-joint","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Shen_Cyclic_Guidance_for_Weakly_Supervised_Joint_Detection_and_Segmentation_CVPR_2019_paper.html","paper_title":"Cyclic Guidance for Weakly Supervised Joint Detection and Segmentation","code":"https://github.com/shenyunhang/WS-JDS","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"PCL-OB-G-Ens + FRCNN","metrics":{"MAP":"44.2"},"uses_additional_data":false,"paper_date":"2018-07-09","paper":"/paper/pcl-proposal-cluster-learning-for-weakly","paper_url":"http://arxiv.org/abs/1807.03342v2","paper_title":"PCL: Proposal Cluster Learning for Weakly Supervised Object Detection","code":"https://github.com/ppengtang/pcl.pytorch","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":6,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":21,"model":"OICR + W-RPN","metrics":{"MAP":"43.2"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/you-reap-what-you-sow-using-videos-to","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Singh_You_Reap_What_You_Sow_Using_Videos_to_Generate_High_CVPR_2019_paper.html","paper_title":"You Reap What You Sow: Using Videos to Generate High Precision Object Proposals for Weakly-Supervised Object Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":22,"model":"ZLDN-L","metrics":{"MAP":"42.9"},"uses_additional_data":false,"paper_date":"2018-04-25","paper":"/paper/zigzag-learning-for-weakly-supervised-object","paper_url":"http://arxiv.org/abs/1804.09466v1","paper_title":"Zigzag Learning for Weakly Supervised Object Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":23,"model":"WebRelETH","metrics":{"MAP":"42.8"},"uses_additional_data":true,"paper_date":"2017-07-27","paper":"/paper/exploiting-web-images-for-weakly-supervised","paper_url":"http://arxiv.org/abs/1707.08721v2","paper_title":"Exploiting Web Images for Weakly Supervised Object Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":24,"model":"OICR-Ens + FRCNN","metrics":{"MAP":"42.5"},"uses_additional_data":false,"paper_date":"2017-04-01","paper":"/paper/multiple-instance-detection-network-with","paper_url":"http://arxiv.org/abs/1704.00138v1","paper_title":"Multiple Instance Detection Network with Online Instance Classifier Refinement","code":"https://github.com/ppengtang/pcl.pytorch","n_code_links":4,"syntology":null},{"rank_in_archive_order":25,"model":"MELM","metrics":{"MAP":"42.4"},"uses_additional_data":false,"paper_date":"2019-02-16","paper":"/paper/min-entropy-latent-model-for-weakly","paper_url":"http://arxiv.org/abs/1902.06057v1","paper_title":"Min-Entropy Latent Model for Weakly Supervised Object Detection","code":"https://github.com/WinFrand/MELM","n_code_links":1,"syntology":null},{"rank_in_archive_order":26,"model":"Deep Self-Taught Learning","metrics":{"MAP":"38.3"},"uses_additional_data":false,"paper_date":"2017-04-18","paper":"/paper/deep-self-taught-learning-for-weakly","paper_url":"http://arxiv.org/abs/1704.05188v2","paper_title":"Deep Self-Taught Learning for Weakly Supervised Object Localization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":27,"model":"WCCN","metrics":{"MAP":"37.9"},"uses_additional_data":false,"paper_date":"2016-11-24","paper":"/paper/weakly-supervised-cascaded-convolutional","paper_url":"http://arxiv.org/abs/1611.08258v1","paper_title":"Weakly Supervised Cascaded Convolutional Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":28,"model":"LM-VGPMIL","metrics":{"MAP":"37.8"},"uses_additional_data":false,"paper_date":"2017-07-01","paper":"/paper/variational-bayesian-multiple-instance","paper_url":"http://openaccess.thecvf.com/content_cvpr_2017/html/Haussmann_Variational_Bayesian_Multiple_CVPR_2017_paper.html","paper_title":"Variational Bayesian Multiple Instance Learning With Gaussian Processes","code":"https://github.com/manuelhaussmann/vgpmil","n_code_links":1,"syntology":null},{"rank_in_archive_order":29,"model":"NSOD","metrics":{"MAP":"36.6"},"uses_additional_data":true,"paper_date":"2019-12-01","paper":"/paper/training-object-detectors-from-few-weakly-1","paper_url":"https://arxiv.org/abs/1912.00384v6","paper_title":"Training Object Detectors from Few Weakly-Labeled and Many Unlabeled Images","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":30,"model":"MSLPD","metrics":{"MAP":"35.4"},"uses_additional_data":false,"paper_date":"2017-06-26","paper":"/paper/few-example-object-detection-with-model","paper_url":"http://arxiv.org/abs/1706.08249v8","paper_title":"Few-Example Object Detection with Model Communication","code":"https://github.com/D-X-Y/DXY-Projects/tree/master/MSPLD","n_code_links":1,"syntology":null},{"rank_in_archive_order":31,"model":"WSDDN + context","metrics":{"MAP":"35.3"},"uses_additional_data":false,"paper_date":"2016-09-14","paper":"/paper/contextlocnet-context-aware-deep-network","paper_url":"http://arxiv.org/abs/1609.04331v1","paper_title":"ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization","code":"https://github.com/vadimkantorov/contextlocnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":32,"model":"Our scheme","metrics":{"MAP":"35.2"},"uses_additional_data":false,"paper_date":"2019-10-04","paper":"/paper/adaptively-denoising-proposal-collection","paper_url":"https://arxiv.org/1910.02101","paper_title":"Adaptively Denoising Proposal Collection forWeakly Supervised Object Localization","code":null,"n_code_links":0,"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":4,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":9,"n_unverified":12,"n_samples":21,"n_pointer_only_licence":9,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":9,"n_unverified":12,"n_samples":21,"n_pointer_only_licence":9,"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"}}}