{"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/adaptation-and-re-identification-network-an","title":"Adaptation and Re-Identification Network: An Unsupervised Deep Transfer Learning Approach to Person Re-Identification","arxiv_id":"1804.09347","date":"2018-04-25","proceeding":null,"authors":["Yu-Jhe Li","Fu-En Yang","Yen-Cheng Liu","Yu-Ying Yeh","Xiaofei Du","Yu-Chiang Frank Wang"],"abstract":"Person re-identification (Re-ID) aims at recognizing the same person from\nimages taken across different cameras. To address this task, one typically\nrequires a large amount labeled data for training an effective Re-ID model,\nwhich might not be practical for real-world applications. To alleviate this\nlimitation, we choose to exploit a sufficient amount of pre-existing labeled\ndata from a different (auxiliary) dataset. By jointly considering such an\nauxiliary dataset and the dataset of interest (but without label information),\nour proposed adaptation and re-identification network (ARN) performs\nunsupervised domain adaptation, which leverages information across datasets and\nderives domain-invariant features for Re-ID purposes. In our experiments, we\nverify that our network performs favorably against state-of-the-art\nunsupervised Re-ID approaches, and even outperforms a number of baseline Re-ID\nmethods which require fully supervised data for training.","url_abs":"http://arxiv.org/abs/1804.09347v1","url_pdf":"http://arxiv.org/pdf/1804.09347v1.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":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-domain-adaptation-on-duke-to","task":"Unsupervised Domain Adaptation","dataset":"Duke to Market","model":"ARN","rank_in_archive_order":20,"of":26,"metrics":{"mAP":"39.4","rank-1":"70.3","rank-10":"86.3","rank-5":"80.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.09347","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}