{"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/strong-but-simple-baseline-with-dual","title":"Strong but Simple Baseline with Dual-Granularity Triplet Loss for Visible-Thermal Person Re-Identification","arxiv_id":"2012.05010","date":"2020-12-09","proceeding":null,"authors":["Haijun Liu","Yanxia Chai","Xiaoheng Tan","Dong Li","Xichuan Zhou"],"abstract":"In this letter, we propose a conceptually simple and effective dual-granularity triplet loss for visible-thermal person re-identification (VT-ReID). In general, ReID models are always trained with the sample-based triplet loss and identification loss from the fine granularity level. It is possible when a center-based loss is introduced to encourage the intra-class compactness and inter-class discrimination from the coarse granularity level. Our proposed dual-granularity triplet loss well organizes the sample-based triplet loss and center-based triplet loss in a hierarchical fine to coarse granularity manner, just with some simple configurations of typical operations, such as pooling and batch normalization. Experiments on RegDB and SYSU-MM01 datasets show that with only the global features our dual-granularity triplet loss can improve the VT-ReID performance by a significant margin. It can be a strong VT-ReID baseline to boost future research with high quality.","url_abs":"https://arxiv.org/abs/2012.05010v2","url_pdf":"https://arxiv.org/pdf/2012.05010v2.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":"strong-but-simple-baseline-with-dual","repo_url":"https://github.com/hijune6/DGTL-for-VT-ReID","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"cross-view-person-re-identification","task_name":"Cross-Modal  Person Re-Identification"},{"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":[{"leaderboard":"/sota/cross-modal-person-re-identification-on-regdb","task":"Cross-Modal  Person Re-Identification","dataset":"RegDB","model":"Dual-granularity-triplet-loss","rank_in_archive_order":2,"of":2,"metrics":{"mAP(V2T)":"73.78","rank1(V2T)":"83.92"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}