{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/style-normalization-and-restitution-for","title":"Style Normalization and Restitution for Generalizable Person Re-identification","arxiv_id":"2005.11037","date":"2020-05-22","proceeding":"CVPR 2020 6","authors":["Xin Jin","Cuiling Lan","Wen-Jun Zeng","Zhibo Chen","Li Zhang"],"abstract":"Existing fully-supervised person re-identification (ReID) methods usually suffer from poor generalization capability caused by domain gaps. The key to solving this problem lies in filtering out identity-irrelevant interference and learning domain-invariant person representations. In this paper, we aim to design a generalizable person ReID framework which trains a model on source domains yet is able to generalize/perform well on target domains. To achieve this goal, we propose a simple yet effective Style Normalization and Restitution (SNR) module. Specifically, we filter out style variations (e.g., illumination, color contrast) by Instance Normalization (IN). However, such a process inevitably removes discriminative information. We propose to distill identity-relevant feature from the removed information and restitute it to the network to ensure high discrimination. For better disentanglement, we enforce a dual causal loss constraint in SNR to encourage the separation of identity-relevant features and identity-irrelevant features. Extensive experiments demonstrate the strong generalization capability of our framework. Our models empowered by the SNR modules significantly outperform the state-of-the-art domain generalization approaches on multiple widely-used person ReID benchmarks, and also show superiority on unsupervised domain adaptation.","url_abs":"https://arxiv.org/abs/2005.11037v1","url_pdf":"https://arxiv.org/pdf/2005.11037v1.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":"style-normalization-and-restitution-for","repo_url":"https://github.com/microsoft/SNR","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"generalizable-person-re-identification","task_name":"Generalizable Person Re-identification"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[{"method_slug":"instance-normalization","method_name":"Instance Normalization"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-domain-adaptation-on-cuhk03-to","task":"Unsupervised Domain Adaptation","dataset":"CUHK03 to MSMT","model":"SNR","rank_in_archive_order":7,"of":7,"metrics":{"R1":"22.0","R10":"-","R5":"-","mAP":"7.7"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-cuhk03-to-1","task":"Unsupervised Domain Adaptation","dataset":"CUHK03 to Market","model":"SNR","rank_in_archive_order":9,"of":9,"metrics":{"R1":"77.8","R10":"-","R5":"-","mAP":"52.4"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-duke-to","task":"Unsupervised Domain Adaptation","dataset":"Duke to Market","model":"SNR","rank_in_archive_order":11,"of":26,"metrics":{"mAP":"61.7","rank-1":"82.8","rank-10":"-","rank-5":"-"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-market-to-6","task":"Unsupervised Domain Adaptation","dataset":"Market to CUHK03","model":"SNR","rank_in_archive_order":7,"of":8,"metrics":{"R1":"17.1","R10":"-","R5":"-","mAP":"17.5"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-market-to","task":"Unsupervised Domain Adaptation","dataset":"Market to Duke","model":"SNR","rank_in_archive_order":9,"of":25,"metrics":{"mAP":"58.1","rank-1":"76.3","rank-10":"-","rank-5":"-"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2005.11037","atlas_url":"https://app.syntology.ai/?focus=2005.11037","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2005.11037"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2005.11037\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2005.11037"},"call":"get_concepts_for_paper(arxiv_id=\"2005.11037\")"}],"by_repo":[{"repo":"microsoft/SNR","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"843583d15b830ac6c22cbc584c6e93c080c7474a44f6c0de9cdc31e47f7fdfb9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}