{"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-a-repression-network-for-precise","title":"Learning a Repression Network for Precise Vehicle Search","arxiv_id":"1708.02386","date":"2017-08-08","proceeding":null,"authors":["Qiantong Xu","Ke Yan","Yonghong Tian"],"abstract":"The growing explosion in the use of surveillance cameras in public security\nhighlights the importance of vehicle search from large-scale image databases.\nPrecise vehicle search, aiming at finding out all instances for a given query\nvehicle image, is a challenging task as different vehicles will look very\nsimilar to each other if they share same visual attributes. To address this\nproblem, we propose the Repression Network (RepNet), a novel multi-task\nlearning framework, to learn discriminative features for each vehicle image\nfrom both coarse-grained and detailed level simultaneously. Besides, benefited\nfrom the satisfactory accuracy of attribute classification, a bucket search\nmethod is proposed to reduce the retrieval time while still maintaining\ncompetitive performance. We conduct extensive experiments on the revised\nVehcileID dataset. Experimental results show that our RepNet achieves the\nstate-of-the-art performance and the bucket search method can reduce the\nretrieval time by about 24 times.","url_abs":"http://arxiv.org/abs/1708.02386v1","url_pdf":"http://arxiv.org/pdf/1708.02386v1.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-a-repression-network-for-precise","repo_url":"https://github.com/may1114/triplet-loss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}