{"url":"/sota/unsupervised-domain-adaptation-on-market-to","task":{"name":"Unsupervised Domain Adaptation","url":"/task/unsupervised-domain-adaptation","note":null},"dataset":{"name":"Market to Duke","url":"/dataset/market-1501"},"category":"Computer Vision","categories":["Computer Vision","Methodology"],"category_note":null,"description":"**Unsupervised Domain Adaptation** is a learning framework to transfer knowledge learned from source domains with a large number of annotated training examples to target domains with unlabeled data only.\r\n\r\n\r\n<span class=\"description-source\">Source: [Domain-Specific Batch Normalization for Unsupervised Domain Adaptation ](https://arxiv.org/abs/1906.03950)</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["mAP","rank-1","rank-5","rank-10"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"mAP":"higher","rank-1":null,"rank-5":null,"rank-10":null}},"counts":{"rows":25,"rows_with_code":17,"rows_with_paper_page":25,"rows_dated":25,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"CORE-ReID","metrics":{"mAP":"74.8","rank-1":"84.8","rank-10":"94.4","rank-5":"92.4"},"uses_additional_data":false,"paper_date":"2024-06-03","paper":"/paper/core-reid-comprehensive-optimization-and","paper_url":"https://www.mdpi.com/2674-113X/3/2/12","paper_title":"CORE-ReID: Comprehensive Optimization and Refinement through Ensemble Fusion in Domain Adaptation for Person Re-Identification","code":"https://github.com/TrinhQuocNguyen/CORE-ReID","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"LF2","metrics":{"mAP":"73.5","rank-1":"83.7"},"uses_additional_data":false,"paper_date":"2022-05-19","paper":"/paper/learning-feature-fusion-for-unsupervised","paper_url":"https://arxiv.org/abs/2205.09495v1","paper_title":"Learning Feature Fusion for Unsupervised Domain Adaptive Person Re-identification","code":"https://github.com/DJEddyking/LF2","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"CCTSE","metrics":{"mAP":"72.6","rank-1":"85.0","rank-10":"93.9","rank-5":"92.1"},"uses_additional_data":false,"paper_date":"2021-03-21","paper":"/paper/unsupervised-and-self-adaptative-techniques","paper_url":"https://arxiv.org/abs/2103.11520v3","paper_title":"Unsupervised and self-adaptative techniques for cross-domain person re-identification","code":"https://github.com/Gabrielcb/Unsupervised_selfAdaptative_ReID","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"EvoADA","metrics":{"mAP":"71.4"},"uses_additional_data":false,"paper_date":"2021-03-25","paper":"/paper/on-evolving-attention-towards-domain","paper_url":"https://arxiv.org/abs/2103.13561v1","paper_title":"On Evolving Attention Towards Domain Adaptation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"AWB","metrics":{"mAP":"71.0","rank-1":"83.4","rank-10":"93.8","rank-5":"91.7"},"uses_additional_data":false,"paper_date":"2020-06-11","paper":"/paper/attentive-waveblock-complementarity-enhanced","paper_url":"https://arxiv.org/abs/2006.06525v3","paper_title":"Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification and Beyond","code":"https://github.com/WangWenhao0716/Attentive-WaveBlock","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"SpCL","metrics":{"mAP":"68.8","rank-1":"82.9","rank-10":"92.5","rank-5":"90.1"},"uses_additional_data":false,"paper_date":"2020-06-04","paper":"/paper/self-paced-contrastive-learning-with-hybrid","paper_url":"https://arxiv.org/abs/2006.02713v2","paper_title":"Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID","code":"https://github.com/open-mmlab/OpenUnReID","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"MMT","metrics":{"mAP":"65.1","rank-1":"78.0","rank-10":"92.5","rank-5":"88.8"},"uses_additional_data":false,"paper_date":"2020-01-06","paper":"/paper/mutual-mean-teaching-pseudo-label-refinery-1","paper_url":"https://arxiv.org/abs/2001.01526v2","paper_title":"Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification","code":"https://github.com/thuml/Transfer-Learning-Library","n_code_links":2,"syntology":{"n_ran":8,"n_unverified":0,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"SDA","metrics":{"mAP":"61.4","rank-1":"76.5","rank-10":"89.7","rank-5":"86.6"},"uses_additional_data":false,"paper_date":"2020-03-14","paper":"/paper/structured-domain-adaptation-for-unsupervised","paper_url":"https://arxiv.org/abs/2003.06650v3","paper_title":"Structured Domain Adaptation with Online Relation Regularization for Unsupervised Person Re-ID","code":"https://github.com/yxgeee/VisDA-ECCV20","n_code_links":3,"syntology":null},{"rank_in_archive_order":9,"model":"SNR","metrics":{"mAP":"58.1","rank-1":"76.3","rank-10":"-","rank-5":"-"},"uses_additional_data":false,"paper_date":"2020-05-22","paper":"/paper/style-normalization-and-restitution-for","paper_url":"https://arxiv.org/abs/2005.11037v1","paper_title":"Style Normalization and Restitution for Generalizable Person Re-identification","code":"https://github.com/microsoft/SNR","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"ACT","metrics":{"mAP":"54.5","rank-1":"72.4","rank-10":"-","rank-5":"-"},"uses_additional_data":false,"paper_date":"2019-12-03","paper":"/paper/asymmetric-co-teaching-for-unsupervised-cross","paper_url":"https://arxiv.org/abs/1912.01349v1","paper_title":"Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification","code":"https://github.com/FlyingRoastDuck/ACT_AAAI20","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"ECN++","metrics":{"mAP":"54.4","rank-1":"74.0","rank-10":"87.4","rank-5":"83.7"},"uses_additional_data":false,"paper_date":"2019-08-01","paper":"/paper/learning-to-adapt-invariance-in-memory-for","paper_url":"https://arxiv.org/abs/1908.00485v1","paper_title":"Learning to Adapt Invariance in Memory for Person Re-identification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"PCB-PAST","metrics":{"mAP":"54.3","rank-1":"72.4"},"uses_additional_data":false,"paper_date":"2019-07-31","paper":"/paper/self-training-with-progressive-augmentation","paper_url":"https://arxiv.org/abs/1907.13315v1","paper_title":"Self-training with progressive augmentation for unsupervised cross-domain person re-identification","code":"https://github.com/zhangxinyu-xyz/PAST-ReID","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"AD-Cluster","metrics":{"mAP":"54.1","rank-1":"72.6","rank-10":"85.5","rank-5":"82.5"},"uses_additional_data":false,"paper_date":"2020-04-19","paper":"/paper/ad-cluster-augmented-discriminative","paper_url":"https://arxiv.org/abs/2004.08787v2","paper_title":"AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"SSG","metrics":{"mAP":"53.4","rank-1":"73.0","rank-10":"83.2","rank-5":"80.6"},"uses_additional_data":false,"paper_date":"2018-11-26","paper":"/paper/one-shot-domain-adaptation-for-person-re","paper_url":"https://arxiv.org/abs/1811.10144v3","paper_title":"Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification","code":"https://github.com/OasisYang/SSG","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"MMCL","metrics":{"mAP":"51.4","rank-1":"72.4","rank-10":"85.0","rank-5":"82.9"},"uses_additional_data":false,"paper_date":"2020-04-20","paper":"/paper/unsupervised-person-re-identification-via-1","paper_url":"https://arxiv.org/abs/2004.09228v1","paper_title":"Unsupervised Person Re-identification via Multi-label Classification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"UDAP","metrics":{"mAP":"49.0","rank-1":"68.4","rank-10":"83.5","rank-5":"80.1"},"uses_additional_data":false,"paper_date":"2018-07-30","paper":"/paper/unsupervised-domain-adaptive-re","paper_url":"http://arxiv.org/abs/1807.11334v1","paper_title":"Unsupervised Domain Adaptive Re-Identification: Theory and Practice","code":"https://github.com/LcDog/DomainAdaptiveReID","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"PDA-Net","metrics":{"mAP":"45.1","rank-1":"63.2","rank-10":"82.5","rank-5":"77.0"},"uses_additional_data":false,"paper_date":"2019-09-20","paper":"/paper/190909675","paper_url":"https://arxiv.org/abs/1909.09675v1","paper_title":"Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":18,"model":"CBN+ECN","metrics":{"mAP":"44.9","rank-1":"68","rank-10":"83.9","rank-5":"80"},"uses_additional_data":false,"paper_date":"2020-01-23","paper":"/paper/disassembling-the-dataset-a-camera-alignment","paper_url":"https://arxiv.org/abs/2001.08680v3","paper_title":"Rethinking the Distribution Gap of Person Re-identification with Camera-based Batch Normalization","code":"https://github.com/automan000/Camera-based-Person-ReID","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"ENC","metrics":{"mAP":"40.4","rank-1":"63.3"},"uses_additional_data":false,"paper_date":"2019-04-03","paper":"/paper/invariance-matters-exemplar-memory-for-domain","paper_url":"http://arxiv.org/abs/1904.01990v1","paper_title":"Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification","code":"https://github.com/zhunzhong07/ECN","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":8,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"UCDA","metrics":{"mAP":"31.0","rank-1":"47.7","rank-10":"-","rank-5":"-"},"uses_additional_data":false,"paper_date":"2019-04-06","paper":"/paper/a-novel-unsupervised-camera-aware-domain","paper_url":"https://arxiv.org/abs/1904.03425v2","paper_title":"A Novel Unsupervised Camera-aware Domain Adaptation Framework for Person Re-identification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"CFSM","metrics":{"mAP":"27.3","rank-1":"49.8","rank-10":"-","rank-5":"-"},"uses_additional_data":false,"paper_date":"2018-12-06","paper":"/paper/disjoint-label-space-transfer-learning-with","paper_url":"http://arxiv.org/abs/1812.02605v1","paper_title":"Disjoint Label Space Transfer Learning with Common Factorised Space","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":22,"model":"DG-Net","metrics":{"mAP":"24.25","rank-1":"42.62","rank-10":"64.63","rank-5":"58.57"},"uses_additional_data":false,"paper_date":"2019-04-15","paper":"/paper/joint-discriminative-and-generative-learning","paper_url":"https://arxiv.org/abs/1904.07223v3","paper_title":"Joint Discriminative and Generative Learning for Person Re-identification","code":"https://github.com/layumi/Person_reID_baseline_pytorch","n_code_links":12,"syntology":{"n_ran":11,"n_unverified":8,"n_samples":19,"n_pointer_only_licence":0}},{"rank_in_archive_order":23,"model":"TJ-AIDL","metrics":{"mAP":"23.0","rank-1":"44.3","rank-10":"65.0","rank-5":"59.6"},"uses_additional_data":false,"paper_date":"2018-03-26","paper":"/paper/transferable-joint-attribute-identity-deep","paper_url":"http://arxiv.org/abs/1803.09786v1","paper_title":"Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":24,"model":"SPGAN","metrics":{"mAP":"22.3","rank-1":"41.1","rank-10":"63.0","rank-5":"56.6"},"uses_additional_data":false,"paper_date":"2017-11-19","paper":"/paper/image-image-domain-adaptation-with-preserved","paper_url":"http://arxiv.org/abs/1711.07027v3","paper_title":"Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification","code":"https://github.com/thuml/Transfer-Learning-Library","n_code_links":2,"syntology":null},{"rank_in_archive_order":25,"model":"OG-Net","metrics":{"mAP":"13.7","rank-1":"26.4","rank-10":"-","rank-5":"-"},"uses_additional_data":false,"paper_date":"2020-06-08","paper":"/paper/person-re-identification-in-the-3d-space","paper_url":"https://arxiv.org/abs/2006.04569v3","paper_title":"Parameter-Efficient Person Re-identification in the 3D Space","code":"https://github.com/layumi/person-reid-3d","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,821 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6821,"papers_extracted_not_yet_verified":65,"boards_without_verdict":29,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":7,"rows_with_any_sample_ran":5,"distinct_papers_with_graph_line":7,"distinct_papers_with_any_sample_ran":5,"samples_over_distinct_papers":{"n_ran":28,"n_unverified":27,"n_samples":55,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":28,"n_unverified":27,"n_samples":55,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}