{"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/learning-chained-deep-features-and","title":"Learning Chained Deep Features and Classifiers for Cascade in Object Detection","arxiv_id":"1702.07054","date":"2017-02-23","proceeding":null,"authors":["Wanli Ouyang","Ku Wang","Xin Zhu","Xiaogang Wang"],"abstract":"Cascade is a widely used approach that rejects obvious negative samples at\nearly stages for learning better classifier and faster inference. This paper\npresents chained cascade network (CC-Net). In this CC-Net, the cascaded\nclassifier at a stage is aided by the classification scores in previous stages.\nFeature chaining is further proposed so that the feature learning for the\ncurrent cascade stage uses the features in previous stages as the prior\ninformation. The chained ConvNet features and classifiers of multiple stages\nare jointly learned in an end-to-end network. In this way, features and\nclassifiers at latter stages handle more difficult samples with the help of\nfeatures and classifiers in previous stages. It yields consistent boost in\ndetection performance on benchmarks like PASCAL VOC 2007 and ImageNet. Combined\nwith better region proposal, CC-Net leads to state-of-the-art result of 81.1%\nmAP on PASCAL VOC 2007.","url_abs":"http://arxiv.org/abs/1702.07054v1","url_pdf":"http://arxiv.org/pdf/1702.07054v1.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":"learning-chained-deep-features-and","repo_url":"https://github.com/wk910930/ccnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"region-proposal","task_name":"Region Proposal"},{"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}