{"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/in-defense-of-the-classification-loss-for","title":"In Defense of the Classification Loss for Person Re-Identification","arxiv_id":"1809.05864","date":"2018-09-16","proceeding":null,"authors":["Yao Zhai","Xun Guo","Yan Lu","Houqiang Li"],"abstract":"The recent research for person re-identification has been focused on two\ntrends. One is learning the part-based local features to form more informative\nfeature descriptors. The other is designing effective metric learning loss\nfunctions such as the triplet loss family. We argue that learning global\nfeatures with classification loss could achieve the same goal, even with some\nsimple and cost-effective architecture design. In this paper, we first explain\nwhy the person re-id framework with standard classification loss usually has\ninferior performance compared to metric learning. Based on that, we further\npropose a person re-id framework featured by channel grouping and multi-branch\nstrategy, which divides global features into multiple channel groups and learns\nthe discriminative channel group features by multi-branch classification\nlayers. The extensive experiments show that our framework outperforms prior\nstate-of-the-arts in terms of both accuracy and inference speed.","url_abs":"http://arxiv.org/abs/1809.05864v2","url_pdf":"http://arxiv.org/pdf/1809.05864v2.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":"in-defense-of-the-classification-loss-for","repo_url":"https://github.com/MARMOTatZJU/ZSLPR-TIANCHI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":null,"task_name":"Triplet"}],"methods":[{"method_slug":"triplet-loss","method_name":"Triplet Loss"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}