{"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/one-shot-domain-adaptation-for-person-re","title":"Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification","arxiv_id":"1811.10144","date":"2018-11-26","proceeding":"ICCV 2019 10","authors":["Yang Fu","Yunchao Wei","Guanshuo Wang","Yuqian Zhou","Honghui Shi","Thomas Huang"],"abstract":"Domain adaptation in person re-identification (re-ID) has always been a challenging task. In this work, we explore how to harness the natural similar characteristics existing in the samples from the target domain for learning to conduct person re-ID in an unsupervised manner. Concretely, we propose a Self-similarity Grouping (SSG) approach, which exploits the potential similarity (from global body to local parts) of unlabeled samples to automatically build multiple clusters from different views. These independent clusters are then assigned with labels, which serve as the pseudo identities to supervise the training process. We repeatedly and alternatively conduct such a grouping and training process until the model is stable. Despite the apparent simplify, our SSG outperforms the state-of-the-arts by more than 4.6% (DukeMTMC to Market1501) and 4.4% (Market1501 to DukeMTMC) in mAP, respectively. Upon our SSG, we further introduce a clustering-guided semisupervised approach named SSG ++ to conduct the one-shot domain adaption in an open set setting (i.e. the number of independent identities from the target domain is unknown). Without spending much effort on labeling, our SSG ++ can further promote the mAP upon SSG by 10.7% and 6.9%, respectively. Our Code is available at: https://github.com/OasisYang/SSG .","url_abs":"https://arxiv.org/abs/1811.10144v3","url_pdf":"https://arxiv.org/pdf/1811.10144v3.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":"one-shot-domain-adaptation-for-person-re","repo_url":"https://github.com/OasisYang/SSG","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"one-shot-learning","task_name":"One-Shot 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-1","task":"Unsupervised Domain Adaptation","dataset":"Duke to MSMT","model":"SSG","rank_in_archive_order":9,"of":13,"metrics":{"mAP":"13.3","rank-1":"32.2","rank-10":"51.2","rank-5":"-"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-duke-to","task":"Unsupervised Domain Adaptation","dataset":"Duke to Market","model":"SSG","rank_in_archive_order":14,"of":26,"metrics":{"mAP":"58.3","rank-1":"80.0","rank-10":"92.4","rank-5":"90.0"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-market-to","task":"Unsupervised Domain Adaptation","dataset":"Market to Duke","model":"SSG","rank_in_archive_order":14,"of":25,"metrics":{"mAP":"53.4","rank-1":"73.0","rank-10":"83.2","rank-5":"80.6"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-market-to-1","task":"Unsupervised Domain Adaptation","dataset":"Market to MSMT","model":"SSG","rank_in_archive_order":13,"of":17,"metrics":{"mAP":"13.2","rank-1":"31.6","rank-10":"49.6","rank-5":"-"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-person-re-identification-on-5","task":"Unsupervised Person Re-Identification","dataset":"DukeMTMC-reID","model":"Self-Similarity Grouping (one shot)","rank_in_archive_order":9,"of":13,"metrics":{"MAP":"55.9","Rank-1":"72.4","Rank-10":"87.7","Rank-5":"84"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-person-re-identification-on-3","task":"Unsupervised Person Re-Identification","dataset":"DukeMTMC-reID->MSMT17","model":"Self-Similarity Grouping (one shot)","rank_in_archive_order":3,"of":7,"metrics":{"Rank-1":"43.6","Rank-10":"61.8","mAP":"23.6"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-person-re-identification-on-4","task":"Unsupervised Person Re-Identification","dataset":"Market-1501","model":"Self-Similarity Grouping (one shot)","rank_in_archive_order":18,"of":23,"metrics":{"MAP":"71.5","Rank-1":"87.5","Rank-10":"96.8","Rank-5":"95.2"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-person-re-identification-on-2","task":"Unsupervised Person Re-Identification","dataset":"Market-1501->MSMT17","model":"Self-Similarity Grouping (one shot)","rank_in_archive_order":4,"of":7,"metrics":{"Rank-1":"27.6","Rank-10":"45.7","mAP":"11.8"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}