{"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/person-transfer-gan-to-bridge-domain-gap-for","title":"Person Transfer GAN to Bridge Domain Gap for Person Re-Identification","arxiv_id":"1711.08565","date":"2017-11-23","proceeding":"CVPR 2018 6","authors":["Longhui Wei","Shiliang Zhang","Wen Gao","Qi Tian"],"abstract":"Although the performance of person Re-Identification (ReID) has been\nsignificantly boosted, many challenging issues in real scenarios have not been\nfully investigated, e.g., the complex scenes and lighting variations, viewpoint\nand pose changes, and the large number of identities in a camera network. To\nfacilitate the research towards conquering those issues, this paper contributes\na new dataset called MSMT17 with many important features, e.g., 1) the raw\nvideos are taken by an 15-camera network deployed in both indoor and outdoor\nscenes, 2) the videos cover a long period of time and present complex lighting\nvariations, and 3) it contains currently the largest number of annotated\nidentities, i.e., 4,101 identities and 126,441 bounding boxes. We also observe\nthat, domain gap commonly exists between datasets, which essentially causes\nsevere performance drop when training and testing on different datasets. This\nresults in that available training data cannot be effectively leveraged for new\ntesting domains. To relieve the expensive costs of annotating new training\nsamples, we propose a Person Transfer Generative Adversarial Network (PTGAN) to\nbridge the domain gap. Comprehensive experiments show that the domain gap could\nbe substantially narrowed-down by the PTGAN.","url_abs":"http://arxiv.org/abs/1711.08565v2","url_pdf":"http://arxiv.org/pdf/1711.08565v2.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":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/ChristmasStory/TransReID-main","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/JeyesHan/P2LR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/RikoLi/PCL-CLIP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/Terminator8758/CAP-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/WangWenhao0716/Attentive-WaveBlock","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/WangWenhao0716/DomainMix","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/casia-iva-lab/pass-reid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/chenhao2345/GCL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/chenhao2345/ICE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/chenhao2345/gcl-extended","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/chequanghuy/Enhancing-Person-Re-Identification-via-UFFM-and-AMC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/damo-cv/TransReID-SSL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/hbchen121/dgreid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/isee-laboratory/pixelfade","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/lithium770/Unsupervised-Person-Re-identification-with-Stochastic-Training-Strategy","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/lithium770/unsupervised-person-re-id-with-stochastic-training-strategy","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/michuanhaohao/transreid-ssl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/stone5265/3c-reid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/syliz517/clip-reid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/template-aware/TAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/theziqi/dccc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/ucas-vg/groupsampling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/wang-pengfei/ucf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/wangyuan249/Mymmt767","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/wavinflaghxm/GroupSampling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/yoonkicho/bau","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/yoonkicho/pplr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/yxgeee/MMT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/yxgeee/SpCL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"person-transfer-gan-to-bridge-domain-gap-for","repo_url":"https://github.com/zkcys001/UDAStrongBaseline","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[{"slug":"msmt17","name":"MSMT17","full_name":"Multi Scene Multi Time dataset for person re-id"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-domain-adaptation-on-duke-to-1","task":"Unsupervised Domain Adaptation","dataset":"Duke to MSMT","model":"PTGAN","rank_in_archive_order":12,"of":13,"metrics":{"mAP":"3.3","rank-1":"11.8","rank-10":"27.4","rank-5":"-"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-market-to-1","task":"Unsupervised Domain Adaptation","dataset":"Market to MSMT","model":"PTGAN","rank_in_archive_order":16,"of":17,"metrics":{"mAP":"2.9","rank-1":"10.2","rank-10":"24.4","rank-5":"-"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-person-re-identification-on-5","task":"Unsupervised Person Re-Identification","dataset":"DukeMTMC-reID","model":"PTGAN","rank_in_archive_order":13,"of":13,"metrics":{"Rank-1":"27.4","Rank-10":"50.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.08565","atlas_url":"https://app.syntology.ai/?focus=1711.08565","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}