{"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/remix-training-generalized-person-re","title":"ReMix: Training Generalized Person Re-identification on a Mixture of Data","arxiv_id":"2410.21938","date":"2024-10-29","proceeding":null,"authors":["Timur Mamedov","Anton Konushin","Vadim Konushin"],"abstract":"Modern person re-identification (Re-ID) methods have a weak generalization ability and experience a major accuracy drop when capturing environments change. This is because existing multi-camera Re-ID datasets are limited in size and diversity, since such data is difficult to obtain. At the same time, enormous volumes of unlabeled single-camera records are available. Such data can be easily collected, and therefore, it is more diverse. Currently, single-camera data is used only for self-supervised pre-training of Re-ID methods. However, the diversity of single-camera data is suppressed by fine-tuning on limited multi-camera data after pre-training. In this paper, we propose ReMix, a generalized Re-ID method jointly trained on a mixture of limited labeled multi-camera and large unlabeled single-camera data. Effective training of our method is achieved through a novel data sampling strategy and new loss functions that are adapted for joint use with both types of data. Experiments show that ReMix has a high generalization ability and outperforms state-of-the-art methods in generalizable person Re-ID. To the best of our knowledge, this is the first work that explores joint training on a mixture of multi-camera and single-camera data in person Re-ID.","url_abs":"https://arxiv.org/abs/2410.21938v1","url_pdf":"https://arxiv.org/pdf/2410.21938v1.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":"diversity","task_name":"Diversity"},{"task_slug":"generalizable-person-re-identification","task_name":"Generalizable Person Re-identification"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/generalizable-person-re-identification-on-22","task":"Generalizable Person Re-identification","dataset":"CUHK03-NP (detected)","model":"ReMix","rank_in_archive_order":3,"of":5,"metrics":{"MSMT17->Rank-1":"27.3","MSMT17->mAP":"27.4","MSMT17-All->Rank-1":"37.7","MSMT17-All->mAP":"37.2","RandPerson->Rank-1":"19.3","RandPerson->mAP":"18.4"},"uses_additional_data":true},{"leaderboard":"/sota/generalizable-person-re-identification-on-23","task":"Generalizable Person Re-identification","dataset":"DukeMTMC-reID","model":"ReMix","rank_in_archive_order":2,"of":4,"metrics":{"MSMT17->Rank1":"71.6","MSMT17->mAP":"52.8","MSMT17-All->Rank-1":"77.6","MSMT17-All->mAP":"61.6","Market-1501->Rank1":"58.4","Market-1501->mAP":"38.8","RandPerson->Rank1":"63.2","RandPerson->mAP":"42.8"},"uses_additional_data":true},{"leaderboard":"/sota/generalizable-person-re-identification-on-21","task":"Generalizable Person Re-identification","dataset":"Market-1501","model":"ReMix","rank_in_archive_order":3,"of":5,"metrics":{"DukeMTMC-reID->Rank1":"71.3","DukeMTMC-reID->mAP":"43.0","MSMT17->Rank-1":"78.2","MSMT17->mAP":"52.4","MSMT17-All->Rank-1":"84.0","MSMT17-All->mAP":"61.0","RandPerson->Rank-1":"72.7","RandPerson->mAP":"45.4"},"uses_additional_data":true},{"leaderboard":"/sota/person-re-identification-on-dukemtmc-reid","task":"Person Re-Identification","dataset":"DukeMTMC-reID","model":"ReMix","rank_in_archive_order":45,"of":94,"metrics":{"Rank-1":"89.6","mAP":"79.8"},"uses_additional_data":true},{"leaderboard":"/sota/person-re-identification-on-msmt17","task":"Person Re-Identification","dataset":"MSMT17","model":"ReMix","rank_in_archive_order":25,"of":43,"metrics":{"Rank-1":"84.8","mAP":"63.9"},"uses_additional_data":true},{"leaderboard":"/sota/person-re-identification-on-market-1501","task":"Person Re-Identification","dataset":"Market-1501","model":"ReMix","rank_in_archive_order":22,"of":135,"metrics":{"Rank-1":"96.2","mAP":"89.8"},"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}