{"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/person-re-identification-by-deep-joint","title":"Person Re-Identification by Deep Joint Learning of Multi-Loss Classification","arxiv_id":"1705.04724","date":"2017-05-12","proceeding":null,"authors":["Wei Li","Xiatian Zhu","Shaogang Gong"],"abstract":"Existing person re-identification (re-id) methods rely mostly on either\nlocalised or global feature representation alone. This ignores their joint\nbenefit and mutual complementary effects. In this work, we show the advantages\nof jointly learning local and global features in a Convolutional Neural Network\n(CNN) by aiming to discover correlated local and global features in different\ncontext. Specifically, we formulate a method for joint learning of local and\nglobal feature selection losses designed to optimise person re-id when using\nonly generic matching metrics such as the L2 distance. We design a novel CNN\narchitecture for Jointly Learning Multi-Loss (JLML) of local and global\ndiscriminative feature optimisation subject concurrently to the same re-id\nlabelled information. Extensive comparative evaluations demonstrate the\nadvantages of this new JLML model for person re-id over a wide range of\nstate-of-the-art re-id methods on five benchmarks (VIPeR, GRID, CUHK01, CUHK03,\nMarket-1501).","url_abs":"http://arxiv.org/abs/1705.04724v2","url_pdf":"http://arxiv.org/pdf/1705.04724v2.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":[],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":"feature-selection","task_name":"feature selection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/person-re-identification-on-market-1501","task":"Person Re-Identification","dataset":"Market-1501","model":"DJL","rank_in_archive_order":104,"of":135,"metrics":{"Rank-1":"85.1","mAP":"65.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.04724","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}