{"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/transferable-joint-attribute-identity-deep","title":"Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification","arxiv_id":"1803.09786","date":"2018-03-26","proceeding":"CVPR 2018 6","authors":["Jingya Wang","Xiatian Zhu","Shaogang Gong","Wei Li"],"abstract":"Most existing person re-identification (re-id) methods require supervised\nmodel learning from a separate large set of pairwise labelled training data for\nevery single camera pair. This significantly limits their scalability and\nusability in real-world large scale deployments with the need for performing\nre-id across many camera views. To address this scalability problem, we develop\na novel deep learning method for transferring the labelled information of an\nexisting dataset to a new unseen (unlabelled) target domain for person re-id\nwithout any supervised learning in the target domain. Specifically, we\nintroduce an Transferable Joint Attribute-Identity Deep Learning (TJ-AIDL) for\nsimultaneously learning an attribute-semantic and identitydiscriminative\nfeature representation space transferrable to any new (unseen) target domain\nfor re-id tasks without the need for collecting new labelled training data from\nthe target domain (i.e. unsupervised learning in the target domain). Extensive\ncomparative evaluations validate the superiority of this new TJ-AIDL model for\nunsupervised person re-id over a wide range of state-of-the-art methods on four\nchallenging benchmarks including VIPeR, PRID, Market-1501, and DukeMTMC-ReID.","url_abs":"http://arxiv.org/abs/1803.09786v1","url_pdf":"http://arxiv.org/pdf/1803.09786v1.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":"attribute","task_name":"Attribute"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"},{"task_slug":"unsupervised-person-re-identification","task_name":"Unsupervised Person Re-Identification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-domain-adaptation-on-duke-to","task":"Unsupervised Domain Adaptation","dataset":"Duke to Market","model":"TJ-AIDL","rank_in_archive_order":24,"of":26,"metrics":{"mAP":"26.5","rank-1":"58.2","rank-10":"81.1","rank-5":"74.8"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-market-to","task":"Unsupervised Domain Adaptation","dataset":"Market to Duke","model":"TJ-AIDL","rank_in_archive_order":23,"of":25,"metrics":{"mAP":"23.0","rank-1":"44.3","rank-10":"65.0","rank-5":"59.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.09786","atlas_url":"https://app.syntology.ai/?focus=1803.09786","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}