{"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/transformer-based-multi-grained-features-for","title":"Transformer Based Multi-Grained Features for Unsupervised Person Re-Identification","arxiv_id":"2211.12280","date":"2022-11-22","proceeding":null,"authors":["Jiachen Li","Menglin Wang","Xiaojin Gong"],"abstract":"Multi-grained features extracted from convolutional neural networks (CNNs) have demonstrated their strong discrimination ability in supervised person re-identification (Re-ID) tasks. Inspired by them, this work investigates the way of extracting multi-grained features from a pure transformer network to address the unsupervised Re-ID problem that is label-free but much more challenging. To this end, we build a dual-branch network architecture based upon a modified Vision Transformer (ViT). The local tokens output in each branch are reshaped and then uniformly partitioned into multiple stripes to generate part-level features, while the global tokens of two branches are averaged to produce a global feature. Further, based upon offline-online associated camera-aware proxies (O2CAP) that is a top-performing unsupervised Re-ID method, we define offline and online contrastive learning losses with respect to both global and part-level features to conduct unsupervised learning. Extensive experiments on three person Re-ID datasets show that the proposed method outperforms state-of-the-art unsupervised methods by a considerable margin, greatly mitigating the gap to supervised counterparts. Code will be available soon at https://github.com/RikoLi/WACV23-workshop-TMGF.","url_abs":"https://arxiv.org/abs/2211.12280v1","url_pdf":"https://arxiv.org/pdf/2211.12280v1.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":"transformer-based-multi-grained-features-for","repo_url":"https://github.com/rikoli/wacv23-workshop-tmgf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":"unsupervised-person-re-identification","task_name":"Unsupervised Person Re-Identification"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-person-re-identification-on-5","task":"Unsupervised Person Re-Identification","dataset":"DukeMTMC-reID","model":"TMGF","rank_in_archive_order":1,"of":13,"metrics":{"MAP":"76.8","Rank-1":"86.7","Rank-10":"94.1","Rank-5":"92.9"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-person-re-identification-on-12","task":"Unsupervised Person Re-Identification","dataset":"MSMT17","model":"TMGF","rank_in_archive_order":2,"of":12,"metrics":{"Rank-1":"83.3","Rank-10":"92.1","Rank-5":"90.2","mAP":"58.2"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-person-re-identification-on-4","task":"Unsupervised Person Re-Identification","dataset":"Market-1501","model":"TMGF","rank_in_archive_order":2,"of":23,"metrics":{"MAP":"89.5","Rank-1":"95.5","Rank-10":"98.7","Rank-5":"98.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.12280","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}