{"url":"/sota/weakly-supervised-object-localization-on-2","task":{"name":"Weakly-Supervised Object Localization","url":"/task/weakly-supervised-object-localization","note":null},"dataset":{"name":"ImageNet","url":"/dataset/imagenet"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Weakly supervised object localization (WSOL) learns to localize objects with only image-level labels, no object level labels (bonding boxes, etc.,) is needed. It is more attractive since image-level labels are much easier and cheaper to obtain.","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":["GT-known localization accuracy","Top-1 Localization Accuracy","average top-1 classification accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"GT-known localization accuracy":"higher","Top-1 Localization Accuracy":"higher","average top-1 classification accuracy":"higher"}},"counts":{"rows":6,"rows_with_code":6,"rows_with_paper_page":6,"rows_dated":6,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"Stable diffusion","metrics":{"GT-known localization accuracy":"75.0","Top-1 Localization Accuracy":"65.2"},"uses_additional_data":true,"paper_date":"2023-07-19","paper":"/paper/generative-prompt-model-for-weakly-supervised","paper_url":"https://arxiv.org/abs/2307.09756v1","paper_title":"Generative Prompt Model for Weakly Supervised Object Localization","code":"https://github.com/callsys/genpromp","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"Deit-S","metrics":{"GT-known localization accuracy":"68.8","Top-1 Localization Accuracy":"56.1","average top-1 classification accuracy":"76.7"},"uses_additional_data":false,"paper_date":"2022-07-21","paper":"/paper/weakly-supervised-object-localization-via","paper_url":"https://arxiv.org/abs/2207.10447v2","paper_title":"Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration","code":"https://github.com/164140757/scm","n_code_links":2,"syntology":{"n_ran":7,"n_unverified":3,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"CexCNN","metrics":{"GT-known localization accuracy":"67.65"},"uses_additional_data":false,"paper_date":"2021-09-13","paper":"/paper/causal-explanation-of-convolutional-neural","paper_url":"https://2021.ecmlpkdd.org/wp-content/uploads/2021/07/sub_287.pdf","paper_title":"Causal Explanation of Convolutional Neural Networks","code":"https://github.com/HichemDebbi/CexCNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"TokenCut","metrics":{"GT-known localization accuracy":"65.4","Top-1 Localization Accuracy":"52.3"},"uses_additional_data":false,"paper_date":"2022-02-23","paper":"/paper/self-supervised-transformers-for-unsupervised","paper_url":"https://arxiv.org/abs/2202.11539v2","paper_title":"Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut","code":"https://github.com/YangtaoWANG95/TokenCut","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"FALcon","metrics":{"GT-known localization accuracy":"62.45","Top-1 Localization Accuracy":"49.39"},"uses_additional_data":false,"paper_date":"2023-12-16","paper":"/paper/exploring-foveation-and-saccade-for-improved","paper_url":"https://proceedings.mlr.press/v226/ibrayev24a.html","paper_title":"Exploring Foveation and Saccade for Improved Weakly-Supervised Localization","code":"https://github.com/TimurIbrayev/FALcon","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"R-Mix (ResNet-50)","metrics":{"Top-1 Localization Accuracy":"55.58"},"uses_additional_data":false,"paper_date":"2022-12-09","paper":"/paper/expeditious-saliency-guided-mix-up-through","paper_url":"https://arxiv.org/abs/2212.04875v3","paper_title":"Expeditious Saliency-guided Mix-up through Random Gradient Thresholding","code":"https://github.com/minhlong94/random-mixup","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"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":3,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":9,"n_unverified":3,"n_samples":12,"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":9,"n_unverified":3,"n_samples":12,"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"}}}