{"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/on-learning-to-localize-objects-with-minimal","title":"On learning to localize objects with minimal supervision","arxiv_id":"1403.1024","date":"2014-03-05","proceeding":null,"authors":["Hyun Oh Song","Ross Girshick","Stefanie Jegelka","Julien Mairal","Zaid Harchaoui","Trevor Darrell"],"abstract":"Learning to localize objects with minimal supervision is an important problem\nin computer vision, since large fully annotated datasets are extremely costly\nto obtain. In this paper, we propose a new method that achieves this goal with\nonly image-level labels of whether the objects are present or not. Our approach\ncombines a discriminative submodular cover problem for automatically\ndiscovering a set of positive object windows with a smoothed latent SVM\nformulation. The latter allows us to leverage efficient quasi-Newton\noptimization techniques. Our experiments demonstrate that the proposed approach\nprovides a 50% relative improvement in mean average precision over the current\nstate-of-the-art on PASCAL VOC 2007 detection.","url_abs":"http://arxiv.org/abs/1403.1024v4","url_pdf":"http://arxiv.org/pdf/1403.1024v4.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":[],"tasks":[{"task_slug":"weakly-supervised-object-detection","task_name":"Weakly Supervised Object Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-object-detection-on-pascal-1","task":"Weakly Supervised Object Detection","dataset":"PASCAL VOC 2007","model":"Cover + SLSVM","rank_in_archive_order":41,"of":41,"metrics":{"MAP":"22.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1403.1024","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}