{"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/how-good-are-detection-proposals-really","title":"How good are detection proposals, really?","arxiv_id":"1406.6962","date":"2014-06-26","proceeding":null,"authors":["Jan Hosang","Rodrigo Benenson","Bernt Schiele"],"abstract":"Current top performing Pascal VOC object detectors employ detection proposals\nto guide the search for objects thereby avoiding exhaustive sliding window\nsearch across images. Despite the popularity of detection proposals, it is\nunclear which trade-offs are made when using them during object detection. We\nprovide an in depth analysis of ten object proposal methods along with four\nbaselines regarding ground truth annotation recall (on Pascal VOC 2007 and\nImageNet 2013), repeatability, and impact on DPM detector performance. Our\nfindings show common weaknesses of existing methods, and provide insights to\nchoose the most adequate method for different settings.","url_abs":"http://arxiv.org/abs/1406.6962v2","url_pdf":"http://arxiv.org/pdf/1406.6962v2.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":"how-good-are-detection-proposals-really","repo_url":"https://github.com/hosang/detection-proposals","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1406.6962","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}