{"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/max-margin-object-detection","title":"Max-Margin Object Detection","arxiv_id":"1502.00046","date":"2015-01-31","proceeding":null,"authors":["Davis E. King"],"abstract":"Most object detection methods operate by applying a binary classifier to\nsub-windows of an image, followed by a non-maximum suppression step where\ndetections on overlapping sub-windows are removed. Since the number of possible\nsub-windows in even moderately sized image datasets is extremely large, the\nclassifier is typically learned from only a subset of the windows. This avoids\nthe computational difficulty of dealing with the entire set of sub-windows,\nhowever, as we will show in this paper, it leads to sub-optimal detector\nperformance.\n  In particular, the main contribution of this paper is the introduction of a\nnew method, Max-Margin Object Detection (MMOD), for learning to detect objects\nin images. This method does not perform any sub-sampling, but instead optimizes\nover all sub-windows. MMOD can be used to improve any object detection method\nwhich is linear in the learned parameters, such as HOG or bag-of-visual-word\nmodels. Using this approach we show substantial performance gains on three\npublicly available datasets. Strikingly, we show that a single rigid HOG filter\ncan outperform a state-of-the-art deformable part model on the Face Detection\nData Set and Benchmark when the HOG filter is learned via MMOD.","url_abs":"http://arxiv.org/abs/1502.00046v1","url_pdf":"http://arxiv.org/pdf/1502.00046v1.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":"max-margin-object-detection","repo_url":"https://github.com/DChaushev/Age-Gender-Recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"max-margin-object-detection","repo_url":"https://github.com/NumericalAdvantage/ld-node-facedetector-2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"max-margin-object-detection","repo_url":"https://github.com/arghadeep25/Face-Detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"max-margin-object-detection","repo_url":"https://github.com/qvdang-dev/Facial-Recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"max-margin-object-detection","repo_url":"https://github.com/qvdang-dev/Facial-Recognizance","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"face-detection","task_name":"Face Detection"},{"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":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}