{"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/deep-transfer-learning-for-person-re","title":"Deep Transfer Learning for Person Re-identification","arxiv_id":"1611.05244","date":"2016-11-16","proceeding":null,"authors":["Mengyue Geng","Yao-Wei Wang","Tao Xiang","Yonghong Tian"],"abstract":"Person re-identification (Re-ID) poses a unique challenge to deep learning:\nhow to learn a deep model with millions of parameters on a small training set\nof few or no labels. In this paper, a number of deep transfer learning models\nare proposed to address the data sparsity problem. First, a deep network\narchitecture is designed which differs from existing deep Re-ID models in that\n(a) it is more suitable for transferring representations learned from large\nimage classification datasets, and (b) classification loss and verification\nloss are combined, each of which adopts a different dropout strategy. Second, a\ntwo-stepped fine-tuning strategy is developed to transfer knowledge from\nauxiliary datasets. Third, given an unlabelled Re-ID dataset, a novel\nunsupervised deep transfer learning model is developed based on co-training.\nThe proposed models outperform the state-of-the-art deep Re-ID models by large\nmargins: we achieve Rank-1 accuracy of 85.4\\%, 83.7\\% and 56.3\\% on CUHK03,\nMarket1501, and VIPeR respectively, whilst on VIPeR, our unsupervised model\n(45.1\\%) beats most supervised models.","url_abs":"http://arxiv.org/abs/1611.05244v2","url_pdf":"http://arxiv.org/pdf/1611.05244v2.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":"deep-transfer-learning-for-person-re","repo_url":"https://github.com/KaiyangZhou/deep-person-reid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}