{"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-to-adapt-invariance-in-memory-for","title":"Learning to Adapt Invariance in Memory for Person Re-identification","arxiv_id":"1908.00485","date":"2019-08-01","proceeding":null,"authors":["Zhun Zhong","Liang Zheng","Zhiming Luo","Shaozi Li","Yi Yang"],"abstract":"This work considers the problem of unsupervised domain adaptation in person re-identification (re-ID), which aims to transfer knowledge from the source domain to the target domain. Existing methods are primary to reduce the inter-domain shift between the domains, which however usually overlook the relations among target samples. This paper investigates into the intra-domain variations of the target domain and proposes a novel adaptation framework w.r.t. three types of underlying invariance, i.e., Exemplar-Invariance, Camera-Invariance, and Neighborhood-Invariance. Specifically, an exemplar memory is introduced to store features of samples, which can effectively and efficiently enforce the invariance constraints over the global dataset. We further present the Graph-based Positive Prediction (GPP) method to explore reliable neighbors for the target domain, which is built upon the memory and is trained on the source samples. Experiments demonstrate that 1) the three invariance properties are indispensable for effective domain adaptation, 2) the memory plays a key role in implementing invariance learning and improves the performance with limited extra computation cost, 3) GPP could facilitate the invariance learning and thus significantly improves the results, and 4) our approach produces new state-of-the-art adaptation accuracy on three re-ID large-scale benchmarks.","url_abs":"https://arxiv.org/abs/1908.00485v1","url_pdf":"https://arxiv.org/pdf/1908.00485v1.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":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-domain-adaptation-on-duke-to-1","task":"Unsupervised Domain Adaptation","dataset":"Duke to MSMT","model":"ECN++","rank_in_archive_order":8,"of":13,"metrics":{"mAP":"16.0","rank-1":"42.5","rank-10":"61.5","rank-5":"55.9"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-duke-to","task":"Unsupervised Domain Adaptation","dataset":"Duke to Market","model":"ECN++","rank_in_archive_order":10,"of":26,"metrics":{"mAP":"63.8","rank-1":"84.1","rank-10":"95.4","rank-5":"92.8"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-market-to","task":"Unsupervised Domain Adaptation","dataset":"Market to Duke","model":"ECN++","rank_in_archive_order":11,"of":25,"metrics":{"mAP":"54.4","rank-1":"74.0","rank-10":"87.4","rank-5":"83.7"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-market-to-1","task":"Unsupervised Domain Adaptation","dataset":"Market to MSMT","model":"ECN++","rank_in_archive_order":11,"of":17,"metrics":{"mAP":"15.2","rank-1":"40.4","rank-10":"58.7","rank-5":"53.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1908.00485","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}