{"url":"/task/weakly-supervised-object-localization","name":"Weakly-Supervised Object Localization","slug":"weakly-supervised-object-localization","description_markdown":"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.","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":140,"papers_with_code":82,"benchmarks":8,"benchmark_tables_in_archive":8,"benchmark_tables_shown":8,"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":3,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/weakly-supervised-object-localization-on-cub","slug":"weakly-supervised-object-localization-on-cub","dataset":"CUB-200-2011","dataset_url":"/dataset/cub-200-2011","rows_in_archive":10,"metrics":["MaxBoxAccV2","Top-1 Localization Accuracy","Top-1 Error Rate","Top-5 Error"],"first_row_in_archive_order":{"model":"DiPS","paper_title":"Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization","paper_url":"/paper/discriminative-sampling-of-proposals-in-self","paper_date":"2022-09-09","arxiv_id":"2209.09209","code_links":[],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-object-localization-on-2","slug":"weakly-supervised-object-localization-on-2","dataset":"ImageNet","dataset_url":"/dataset/imagenet","rows_in_archive":6,"metrics":["GT-known localization accuracy","Top-1 Localization Accuracy","average top-1 classification accuracy"],"first_row_in_archive_order":{"model":"Stable diffusion","paper_title":"Generative Prompt Model for Weakly Supervised Object Localization","paper_url":"/paper/generative-prompt-model-for-weakly-supervised","paper_date":"2023-07-19","arxiv_id":"2307.09756","code_links":[{"title":"callsys/genpromp","url":"https://github.com/callsys/genpromp"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/weakly-supervised-object-localization-on-1","slug":"weakly-supervised-object-localization-on-1","dataset":"ILSVRC 2016","dataset_url":null,"rows_in_archive":4,"metrics":["Top-5 Error"],"first_row_in_archive_order":{"model":"SPG","paper_title":"Self-produced Guidance for Weakly-supervised Object Localization","paper_url":"/paper/self-produced-guidance-for-weakly-supervised","paper_date":"2018-07-24","arxiv_id":"1807.08902","code_links":[{"title":"xiaomengyc/SPG","url":"https://github.com/xiaomengyc/SPG"}],"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/weakly-supervised-object-localization-on-cub-2","slug":"weakly-supervised-object-localization-on-cub-2","dataset":"CUB-200-2011","dataset_url":"/dataset/cub-200-2011","rows_in_archive":3,"metrics":["GT-known localization accuracy","Top-1 Localization Accuracy","average top-1 classification accuracy"],"first_row_in_archive_order":{"model":"FALcon","paper_title":"Exploring Foveation and Saccade for Improved Weakly-Supervised Localization","paper_url":"/paper/exploring-foveation-and-saccade-for-improved","paper_date":"2023-12-16","arxiv_id":null,"code_links":[{"title":"TimurIbrayev/FALcon","url":"https://github.com/TimurIbrayev/FALcon"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-object-localization-on-tiny","slug":"weakly-supervised-object-localization-on-tiny","dataset":"Tiny ImageNet","dataset_url":"/dataset/tiny-imagenet","rows_in_archive":3,"metrics":["Top-1 Localization Accuracy"],"first_row_in_archive_order":{"model":"InfoCAM","paper_title":"Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator","paper_url":"/paper/rethinking-softmax-with-cross-entropy-neural","paper_date":"2019-11-25","arxiv_id":"1911.10688","code_links":[{"title":"ZhenyueQin/Research-Softmax-with-Mutual-Information","url":"https://github.com/ZhenyueQin/Research-Softmax-with-Mutual-Information"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-object-localization-on","slug":"weakly-supervised-object-localization-on","dataset":"ILSVRC 2015","dataset_url":null,"rows_in_archive":2,"metrics":["Top-1 Error Rate"],"first_row_in_archive_order":{"model":"SPG","paper_title":"Self-produced Guidance for Weakly-supervised Object Localization","paper_url":"/paper/self-produced-guidance-for-weakly-supervised","paper_date":"2018-07-24","arxiv_id":"1807.08902","code_links":[{"title":"xiaomengyc/SPG","url":"https://github.com/xiaomengyc/SPG"}],"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/weakly-supervised-object-localization-on-4","slug":"weakly-supervised-object-localization-on-4","dataset":"ImageNet-100 - 50 classes + 5 steps of 10 classes","dataset_url":null,"rows_in_archive":1,"metrics":["Average Top-1 localization accuracy"],"first_row_in_archive_order":{"model":"FDCNet","paper_title":"FDCNet: Feature Drift Compensation Network for Class-Incremental Weakly Supervised Object Localization","paper_url":"/paper/fdcnet-feature-drift-compensation-network-for","paper_date":"2023-09-17","arxiv_id":"2309.09122","code_links":[{"title":"Vision-sejin/FDCNet","url":"https://github.com/Vision-sejin/FDCNet"}],"syntology":null}},{"leaderboard":"/sota/weakly-supervised-object-localization-on-cub-1","slug":"weakly-supervised-object-localization-on-cub-1","dataset":"CUB","dataset_url":"/dataset/cub-200-2011","rows_in_archive":1,"metrics":["Top-1 Localization Accuracy"],"first_row_in_archive_order":{"model":"TokenCut","paper_title":"Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut","paper_url":"/paper/self-supervised-transformers-for-unsupervised","paper_date":"2022-02-23","arxiv_id":"2202.11539","code_links":[{"title":"YangtaoWANG95/TokenCut","url":"https://github.com/YangtaoWANG95/TokenCut"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/imagenet","name":"ImageNet","full_name":"","num_papers_in_archive":15430},{"url":"/dataset/cub-200-2011","name":"CUB-200-2011","full_name":"Caltech-UCSD Birds-200-2011","num_papers_in_archive":2235},{"url":"/dataset/tiny-imagenet","name":"Tiny ImageNet","full_name":"Tiny ImageNet","num_papers_in_archive":1232}],"subtasks":[],"parent_tasks":[{"url":"/task/object-localization","name":"Object Localization"}],"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":82,"tagged_in_all":140,"items":[{"url":"/paper/learning-deep-features-for-discriminative","title":"Learning Deep Features for Discriminative Localization","date":"2015-12-14","arxiv_id":"1512.04150","repositories_listed":35,"syntology":{"n":17,"n_ran":2,"n_unverified":15,"n_pointer_only":3}},{"url":"/paper/layercam-exploring-hierarchical-class","title":"LayerCAM: Exploring Hierarchical Class Activation Maps for Localization","date":"2021-06-22","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/eigen-cam-class-activation-map-using","title":"Eigen-CAM: Class Activation Map using Principal Components","date":"2020-08-01","arxiv_id":"2008.00299","repositories_listed":3,"syntology":null},{"url":"/paper/hide-and-seek-forcing-a-network-to-be","title":"Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization","date":"2017-04-13","arxiv_id":"1704.04232","repositories_listed":3,"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/weakly-supervised-object-localization-via","title":"Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration","date":"2022-07-21","arxiv_id":"2207.10447","repositories_listed":2,"syntology":{"n":10,"n_ran":7,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/contrastive-learning-of-class-agnostic","title":"Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation","date":"2022-03-25","arxiv_id":"2203.13505","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/background-activation-suppression-for-weakly","title":"Background Activation Suppression for Weakly Supervised Object Localization","date":"2021-12-01","arxiv_id":"2112.00580","repositories_listed":2,"syntology":null},{"url":"/paper/localizing-objects-with-self-supervised","title":"Localizing Objects with Self-Supervised Transformers and no Labels","date":"2021-09-29","arxiv_id":"2109.14279","repositories_listed":2,"syntology":null},{"url":"/paper/2103-14862","title":"TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization","date":"2021-03-27","arxiv_id":"2103.14862","repositories_listed":2,"syntology":null},{"url":"/paper/a-generic-visualization-approach-for","title":"A Generic Visualization Approach for Convolutional Neural Networks","date":"2020-07-19","arxiv_id":"2007.09748","repositories_listed":2,"syntology":null},{"url":"/paper/evaluation-for-weakly-supervised-object","title":"Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets","date":"2020-07-08","arxiv_id":"2007.04178","repositories_listed":2,"syntology":null},{"url":"/paper/evaluating-weakly-supervised-object","title":"Evaluating Weakly Supervised Object Localization Methods Right","date":"2020-01-21","arxiv_id":"2001.07437","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/adversarial-complementary-learning-for-weakly","title":"Adversarial Complementary Learning for Weakly Supervised Object Localization","date":"2018-04-19","arxiv_id":"1804.06962","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"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/pixelcam-pixel-class-activation-mapping-for","title":"PixelCAM: Pixel Class Activation Mapping for Histology Image Classification and ROI Localization","date":"2025-03-31","arxiv_id":"2503.24135","repositories_listed":1,"syntology":null},{"url":"/paper/ted-loc-text-distillation-for-weakly","title":"TeD-Loc: Text Distillation for Weakly Supervised Object Localization","date":"2025-01-22","arxiv_id":"2501.12632","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-transformers-for-weakly-supervised","title":"Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos","date":"2024-07-08","arxiv_id":"2407.06018","repositories_listed":1,"syntology":null},{"url":"/paper/se3d-a-framework-for-saliency-method","title":"SE3D: A Framework For Saliency Method Evaluation In 3D Imaging","date":"2024-05-23","arxiv_id":"2405.14584","repositories_listed":1,"syntology":null},{"url":"/paper/source-free-domain-adaptation-of-weakly","title":"Source-Free Domain Adaptation of Weakly-Supervised Object Localization Models for Histology","date":"2024-04-29","arxiv_id":"2404.19113","repositories_listed":1,"syntology":null},{"url":"/paper/realistic-model-selection-for-weakly","title":"A Realistic Protocol for Evaluation of Weakly Supervised Object Localization","date":"2024-04-15","arxiv_id":"2404.10034","repositories_listed":1,"syntology":null},{"url":"/paper/cam-back-again-large-kernel-cnns-from-a","title":"CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspective","date":"2024-03-11","arxiv_id":"2403.06676","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-foveation-and-saccade-for-improved","title":"Exploring Foveation and Saccade for Improved Weakly-Supervised Localization","date":"2023-12-16","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dips-discriminative-pseudo-label-sampling","title":"DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object Localization","date":"2023-10-09","arxiv_id":"2310.06196","repositories_listed":1,"syntology":null},{"url":"/paper/fdcnet-feature-drift-compensation-network-for","title":"FDCNet: Feature Drift Compensation Network for Class-Incremental Weakly Supervised Object Localization","date":"2023-09-17","arxiv_id":"2309.09122","repositories_listed":1,"syntology":null},{"url":"/paper/generative-prompt-model-for-weakly-supervised","title":"Generative Prompt Model for Weakly Supervised Object Localization","date":"2023-07-19","arxiv_id":"2307.09756","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/open-world-weakly-supervised-object","title":"Open-World Weakly-Supervised Object Localization","date":"2023-04-17","arxiv_id":"2304.08271","repositories_listed":1,"syntology":null},{"url":"/paper/spatial-aware-token-for-weakly-supervised","title":"Spatial-Aware Token for Weakly Supervised Object Localization","date":"2023-03-18","arxiv_id":"2303.10438","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_unverified":1,"n_pointer_only":6}},{"url":"/paper/further-improving-weakly-supervised-object","title":"Knowledge-guided Causal Intervention for Weakly-supervised Object Localization","date":"2023-01-03","arxiv_id":"2301.01060","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-normalization-i-can-visualize","title":"Adversarial Normalization: I Can Visualize Everything (ICE)","date":"2023-01-01","arxiv_id":null,"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"}}