{"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/building-computationally-efficient-and-well","title":"Building Computationally Efficient and Well-Generalizing Person Re-Identification Models with Metric Learning","arxiv_id":"2003.07618","date":"2020-03-17","proceeding":"Submitted to International Conference on Pattern Recognition (ICPR 2020) 2020 3","authors":["Vladislav Sovrasov","Dmitry Sidnev"],"abstract":"This work considers the problem of domain shift in person re-identification.Being trained on one dataset, a re-identification model usually performs much worse on unseen data. Partially this gap is caused by the relatively small scale of person re-identification datasets (compared to face recognition ones, for instance), but it is also related to training objectives. We propose to use the metric learning objective, namely AM-Softmax loss, and some additional training practices to build well-generalizing, yet, computationally efficient models. We use recently proposed Omni-Scale Network (OSNet) architecture combined with several training tricks and architecture adjustments to obtain state-of-the art results in cross-domain generalization problem on a large-scale MSMT17 dataset in three setups: MSMT17-all->DukeMTMC, MSMT17-train->Market1501 and MSMT17-all->Market1501.","url_abs":"https://arxiv.org/abs/2003.07618v2","url_pdf":"https://arxiv.org/pdf/2003.07618v2.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":"building-computationally-efficient-and-well","repo_url":"https://github.com/opencv/openvino_training_extensions","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/person-re-identification-on-msmt17","task":"Person Re-Identification","dataset":"MSMT17","model":"OSNet-IAP 1.0x","rank_in_archive_order":37,"of":43,"metrics":{"Rank-1":"77.97","mAP":"48.66"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.07618","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}