{"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/deepbox-learning-objectness-with","title":"DeepBox: Learning Objectness with Convolutional Networks","arxiv_id":"1505.02146","date":"2015-05-08","proceeding":"ICCV 2015 12","authors":["Wei-cheng Kuo","Bharath Hariharan","Jitendra Malik"],"abstract":"Existing object proposal approaches use primarily bottom-up cues to rank\nproposals, while we believe that objectness is in fact a high level construct.\nWe argue for a data-driven, semantic approach for ranking object proposals. Our\nframework, which we call DeepBox, uses convolutional neural networks (CNNs) to\nrerank proposals from a bottom-up method. We use a novel four-layer CNN\narchitecture that is as good as much larger networks on the task of evaluating\nobjectness while being much faster. We show that DeepBox significantly improves\nover the bottom-up ranking, achieving the same recall with 500 proposals as\nachieved by bottom-up methods with 2000. This improvement generalizes to\ncategories the CNN has never seen before and leads to a 4.5-point gain in\ndetection mAP. Our implementation achieves this performance while running at\n260 ms per image.","url_abs":"http://arxiv.org/abs/1505.02146v2","url_pdf":"http://arxiv.org/pdf/1505.02146v2.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":"deepbox-learning-objectness-with","repo_url":"https://github.com/weichengkuo/DeepBox","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1505.02146","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}