{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/multiple-instance-learning-on-deep-features","title":"Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts","arxiv_id":"2008.01178","date":"2020-08-03","proceeding":null,"authors":["Nicolas Gonthier","Saïd Ladjal","Yann Gousseau"],"abstract":"Weakly supervised object detection (WSOD) using only image-level annotations has attracted a growing attention over the past few years. Whereas such task is typically addressed with a domain-specific solution focused on natural images, we show that a simple multiple instance approach applied on pre-trained deep features yields excellent performances on non-photographic datasets, possibly including new classes. The approach does not include any fine-tuning or cross-domain learning and is therefore efficient and possibly applicable to arbitrary datasets and classes. We investigate several flavors of the proposed approach, some including multi-layers perceptron and polyhedral classifiers. Despite its simplicity, our method shows competitive results on a range of publicly available datasets, including paintings (People-Art, IconArt), watercolors, cliparts and comics and allows to quickly learn unseen visual categories.","url_abs":"https://arxiv.org/abs/2008.01178v5","url_pdf":"https://arxiv.org/pdf/2008.01178v5.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"multiple-instance-learning-on-deep-features","repo_url":"https://github.com/nicaogr/Mi_max","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"multiple-instance-learning-on-deep-features","repo_url":"https://github.com/ngonthier/Mi_max","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"multiple-instance-learning","task_name":"Multiple Instance Learning"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"weakly-supervised-object-detection","task_name":"Weakly Supervised Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-object-detection-on-5","task":"Weakly Supervised Object Detection","dataset":"CASPAPaintings","model":"MI-max","rank_in_archive_order":1,"of":1,"metrics":{"Mean mAP":"16.2"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-object-detection-on-2","task":"Weakly Supervised Object Detection","dataset":"Clipart1k","model":"MI-max","rank_in_archive_order":7,"of":7,"metrics":{"MAP":"38.4"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-object-detection-on-comic2k","task":"Weakly Supervised Object Detection","dataset":"Comic2k","model":"MI-max","rank_in_archive_order":8,"of":8,"metrics":{"MAP":"27"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-object-detection-on-iconart","task":"Weakly Supervised Object Detection","dataset":"IconArt","model":"MI_Net [wang_revisiting_2018]","rank_in_archive_order":1,"of":2,"metrics":{"MAP":"15.1"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-object-detection-on-3","task":"Weakly Supervised Object Detection","dataset":"PeopleArt","model":"Polyhedral MI-max","rank_in_archive_order":1,"of":2,"metrics":{"MAP":"58.3"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-object-detection-on-1","task":"Weakly Supervised Object Detection","dataset":"Watercolor2k","model":"MI-max","rank_in_archive_order":11,"of":12,"metrics":{"MAP":"49.5"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}