{"url":"/sota/weakly-supervised-object-detection-on-2","task":{"name":"Weakly Supervised Object Detection","url":"/task/weakly-supervised-object-detection","note":null},"dataset":{"name":"Clipart1k","url":"/dataset/clipart1k"},"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":7,"rows_with_code":6,"rows_with_paper_page":7,"rows_dated":7,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"H2FA R-CNN (clipart_all)","metrics":{"MAP":"69.8"},"uses_additional_data":false,"paper_date":"2022-01-01","paper":"/paper/h2fa-r-cnn-holistic-and-hierarchical-feature","paper_url":"http://openaccess.thecvf.com//content/CVPR2022/html/Xu_H2FA_R-CNN_Holistic_and_Hierarchical_Feature_Alignment_for_Cross-Domain_Weakly_CVPR_2022_paper.html","paper_title":"H2FA R-CNN: Holistic and Hierarchical Feature Alignment for Cross-Domain Weakly Supervised Object Detection","code":"https://github.com/xuyunqiu/h2fa_r-cnn","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"DASS-Detector (YOLOX Tiny)","metrics":{"MAP":"64.25"},"uses_additional_data":false,"paper_date":"2022-11-19","paper":"/paper/domain-adaptive-self-supervised-pre-training","paper_url":"https://arxiv.org/abs/2211.10641v2","paper_title":"Domain-Adaptive Self-Supervised Pre-Training for Face & Body Detection in Drawings","code":"https://github.com/barisbatuhan/dass_det_inference","n_code_links":2,"syntology":null},{"rank_in_archive_order":3,"model":"H2FA R-CNN (clipart_test)","metrics":{"MAP":"55.3"},"uses_additional_data":false,"paper_date":"2022-01-01","paper":"/paper/h2fa-r-cnn-holistic-and-hierarchical-feature","paper_url":"http://openaccess.thecvf.com//content/CVPR2022/html/Xu_H2FA_R-CNN_Holistic_and_Hierarchical_Feature_Alignment_for_Cross-Domain_Weakly_CVPR_2022_paper.html","paper_title":"H2FA R-CNN: Holistic and Hierarchical Feature Alignment for Cross-Domain Weakly Supervised Object Detection","code":"https://github.com/xuyunqiu/h2fa_r-cnn","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"ICCM","metrics":{"MAP":"46.7"},"uses_additional_data":false,"paper_date":"2021-06-19","paper":"/paper/informative-and-consistent-correspondence","paper_url":"http://openaccess.thecvf.com//content/CVPR2021/html/Hou_Informative_and_Consistent_Correspondence_Mining_for_Cross-Domain_Weakly_Supervised_Object_CVPR_2021_paper.html","paper_title":"Informative and Consistent Correspondence Mining for Cross-Domain Weakly Supervised Object Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"DT+PL","metrics":{"MAP":"46.0"},"uses_additional_data":false,"paper_date":"2018-03-30","paper":"/paper/cross-domain-weakly-supervised-object","paper_url":"http://arxiv.org/abs/1803.11365v1","paper_title":"Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation","code":"https://github.com/naoto0804/cross-domain-detection","n_code_links":3,"syntology":{"n_ran":1,"n_unverified":10,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"MEAA","metrics":{"MAP":"41.1"},"uses_additional_data":true,"paper_date":"2020-10-31","paper":"/paper/domain-adaptive-object-detection-via-1","paper_url":"https://dl.acm.org/doi/10.1145/3394171.3413553","paper_title":"Domain-Adaptive Object Detection via Uncertainty-Aware Distribution Alignment","code":"https://github.com/basiclab/DA-OD-MEAA-PyTorch","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"MI-max","metrics":{"MAP":"38.4"},"uses_additional_data":false,"paper_date":"2020-08-03","paper":"/paper/multiple-instance-learning-on-deep-features","paper_url":"https://arxiv.org/abs/2008.01178v5","paper_title":"Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts","code":"https://github.com/ngonthier/Mi_max","n_code_links":2,"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":1,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":1,"n_unverified":10,"n_samples":11,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":1,"n_unverified":10,"n_samples":11,"n_pointer_only_licence":0,"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"}}}