{"url":"/sota/domain-adaptation-on-visda2017","task":{"name":"Domain Adaptation","url":"/task/domain-adaptation","note":null},"dataset":{"name":"VisDA2017","url":"/dataset/visda-2017"},"category":"Computer Vision","categories":["Computer Vision","Methodology"],"category_note":null,"description":"**Domain Adaptation** is the task of adapting models across domains. This is motivated by the challenge where the test and training datasets fall from different data distributions due to some factor. Domain adaptation aims to build machine learning models that can be generalized into a target domain and dealing with the discrepancy across domain distributions. \r\n\r\nFurther readings:\r\n\r\n- [A Brief Review of Domain Adaptation](https://paperswithcode.com/paper/a-brief-review-of-domain-adaptation)\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Unsupervised Image-to-Image Translation Networks](https://arxiv.org/pdf/1703.00848v6.pdf) )</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":["Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher"}},"counts":{"rows":28,"rows_with_code":26,"rows_with_paper_page":28,"rows_dated":28,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"FFTAT","metrics":{"Accuracy":"93.8"},"uses_additional_data":false,"paper_date":"2024-11-10","paper":"/paper/feature-fusion-transferability-aware","paper_url":"https://arxiv.org/abs/2411.07794v1","paper_title":"Feature Fusion Transferability Aware Transformer for Unsupervised Domain Adaptation","code":"https://github.com/Shawey94/NoisyNN","n_code_links":2,"syntology":null},{"rank_in_archive_order":2,"model":"RCL","metrics":{"Accuracy":"93.2"},"uses_additional_data":false,"paper_date":"2024-05-28","paper":"/paper/empowering-source-free-domain-adaptation-with","paper_url":"https://arxiv.org/abs/2405.18376v1","paper_title":"Empowering Source-Free Domain Adaptation with MLLM-driven Curriculum Learning","code":"https://github.com/Dong-Jie-Chen/RCL","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"MIC","metrics":{"Accuracy":"92.8"},"uses_additional_data":false,"paper_date":"2022-12-02","paper":"/paper/mic-masked-image-consistency-for-context","paper_url":"https://arxiv.org/abs/2212.01322v2","paper_title":"MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation","code":"https://github.com/lhoyer/mic","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"SWG","metrics":{"Accuracy":"92.7"},"uses_additional_data":false,"paper_date":"2023-12-07","paper":"/paper/combining-inherent-knowledge-of-vision","paper_url":"https://arxiv.org/abs/2312.04066v4","paper_title":"Combining inherent knowledge of vision-language models with unsupervised domain adaptation through strong-weak guidance","code":"https://github.com/ThomasWestfechtel/SWG","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"CMKD","metrics":{"Accuracy":"91.8"},"uses_additional_data":false,"paper_date":"2024-04-19","paper":"/paper/unsupervised-domain-adaption-harnessing","paper_url":"https://ieeexplore.ieee.org/document/10505301","paper_title":"Unsupervised Domain Adaption Harnessing Vision-Language Pre-training","code":"https://github.com/Wenlve-Zhou/VLP-UDA","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"DePT","metrics":{"Accuracy":"90.7"},"uses_additional_data":false,"paper_date":"2022-10-10","paper":"/paper/visual-prompt-tuning-for-test-time-domain","paper_url":"https://arxiv.org/abs/2210.04831v2","paper_title":"Visual Prompt Tuning for Test-time Domain Adaptation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"SDAT(ViT)","metrics":{"Accuracy":"89.8"},"uses_additional_data":false,"paper_date":"2022-06-16","paper":"/paper/a-closer-look-at-smoothness-in-domain-1","paper_url":"https://arxiv.org/abs/2206.08213v1","paper_title":"A Closer Look at Smoothness in Domain Adversarial Training","code":"https://github.com/val-iisc/sdat","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"SFDA2++","metrics":{"Accuracy":"89.6"},"uses_additional_data":false,"paper_date":"2024-03-16","paper":"/paper/sf-da-2-source-free-domain-adaptation-through","paper_url":"https://arxiv.org/abs/2403.10834v1","paper_title":"SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation","code":"https://github.com/shinyflight/sfda2","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":4,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":9,"model":"PMtrans","metrics":{"Accuracy":"88.8"},"uses_additional_data":false,"paper_date":"2023-03-23","paper":"/paper/patch-mix-transformer-for-unsupervised-domain","paper_url":"https://arxiv.org/abs/2303.13434v2","paper_title":"Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"CoVi","metrics":{"Accuracy":"88.5"},"uses_additional_data":false,"paper_date":"2021-11-26","paper":"/paper/contrastive-vicinal-space-for-unsupervised","paper_url":"https://arxiv.org/abs/2111.13353v3","paper_title":"Contrastive Vicinal Space for Unsupervised Domain Adaptation","code":"https://github.com/najaemin92/covi","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"CDTrans","metrics":{"Accuracy":"88.4"},"uses_additional_data":false,"paper_date":"2021-09-13","paper":"/paper/cdtrans-cross-domain-transformer-for","paper_url":"https://arxiv.org/abs/2109.06165v4","paper_title":"CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation","code":"https://github.com/cdtrans/cdtrans","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":7,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"SFDA2","metrics":{"Accuracy":"88.1"},"uses_additional_data":false,"paper_date":"2024-03-16","paper":"/paper/sf-da-2-source-free-domain-adaptation-through","paper_url":"https://arxiv.org/abs/2403.10834v1","paper_title":"SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation","code":"https://github.com/shinyflight/sfda2","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":4,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":13,"model":"FixBi","metrics":{"Accuracy":"87.2"},"uses_additional_data":false,"paper_date":"2020-11-18","paper":"/paper/fixbi-bridging-domain-spaces-for-unsupervised","paper_url":"https://arxiv.org/abs/2011.09230v2","paper_title":"FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation","code":"https://github.com/najaemin92/fixbi","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"CAN","metrics":{"Accuracy":"87.2"},"uses_additional_data":false,"paper_date":"2019-01-04","paper":"/paper/contrastive-adaptation-network-for","paper_url":"http://arxiv.org/abs/1901.00976v2","paper_title":"Contrastive Adaptation Network for Unsupervised Domain Adaptation","code":"https://github.com/kgl-prml/Contrastive-Adaptation-Network-for-Unsupervised-Domain-Adaptation","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"dSNE","metrics":{"Accuracy":"86.15"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/d-sne-domain-adaptation-using-stochastic","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Xu_d-SNE_Domain_Adaptation_Using_Stochastic_Neighborhood_Embedding_CVPR_2019_paper.html","paper_title":"d-SNE: Domain Adaptation Using Stochastic Neighborhood Embedding","code":"https://github.com/aws-samples/d-SNE","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"CPGA","metrics":{"Accuracy":"86.0"},"uses_additional_data":false,"paper_date":"2021-06-18","paper":"/paper/source-free-domain-adaptation-via-avatar","paper_url":"https://arxiv.org/abs/2106.15326v1","paper_title":"Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation","code":"https://github.com/SCUT-AILab/CPGA","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"Mean teacher","metrics":{"Accuracy":"85.4"},"uses_additional_data":false,"paper_date":"2017-06-16","paper":"/paper/self-ensembling-for-visual-domain-adaptation","paper_url":"http://arxiv.org/abs/1706.05208v4","paper_title":"Self-ensembling for visual domain adaptation","code":"https://github.com/thuml/Transfer-Learning-Library","n_code_links":3,"syntology":null},{"rank_in_archive_order":18,"model":"MCC+NWD","metrics":{"Accuracy":"83.7"},"uses_additional_data":false,"paper_date":"2022-04-08","paper":"/paper/reusing-the-task-specific-classifier-as-a","paper_url":"https://arxiv.org/abs/2204.03838v1","paper_title":"Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation","code":"https://github.com/xiaoachen98/daln","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":19,"model":"SHOT","metrics":{"Accuracy":"82.9"},"uses_additional_data":false,"paper_date":"2020-02-20","paper":"/paper/do-we-really-need-to-access-the-source-data","paper_url":"https://arxiv.org/abs/2002.08546v6","paper_title":"Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation","code":"https://github.com/tim-learn/SHOT","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":20,"model":"DTA","metrics":{"Accuracy":"81.5"},"uses_additional_data":false,"paper_date":"2019-10-12","paper":"/paper/drop-to-adapt-learning-discriminative","paper_url":"https://arxiv.org/abs/1910.05562v1","paper_title":"Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation","code":"https://github.com/postBG/DTA.pytorch","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"MRKLD + LRENT","metrics":{"Accuracy":"78.1"},"uses_additional_data":false,"paper_date":"2019-08-26","paper":"/paper/confidence-regularized-self-training","paper_url":"https://arxiv.org/abs/1908.09822v3","paper_title":"Confidence Regularized Self-Training","code":"https://github.com/yzou2/CRST","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":22,"model":"CRST","metrics":{"Accuracy":"78.1"},"uses_additional_data":false,"paper_date":"2019-08-26","paper":"/paper/confidence-regularized-self-training","paper_url":"https://arxiv.org/abs/1908.09822v3","paper_title":"Confidence Regularized Self-Training","code":"https://github.com/yzou2/CRST","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":23,"model":"SENTRY (ResNet50)","metrics":{"Accuracy":"76.7"},"uses_additional_data":false,"paper_date":"2020-12-21","paper":"/paper/sentry-selective-entropy-optimization-via","paper_url":"https://arxiv.org/abs/2012.11460v2","paper_title":"SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptation","code":"https://github.com/virajprabhu/SENTRY","n_code_links":2,"syntology":null},{"rank_in_archive_order":24,"model":"SWD","metrics":{"Accuracy":"76.4"},"uses_additional_data":false,"paper_date":"2019-03-10","paper":"/paper/sliced-wasserstein-discrepancy-for","paper_url":"http://arxiv.org/abs/1903.04064v1","paper_title":"Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation","code":"https://github.com/kevinmusgrave/pytorch-adapt","n_code_links":2,"syntology":null},{"rank_in_archive_order":25,"model":"IAFN","metrics":{"Accuracy":"76.1"},"uses_additional_data":false,"paper_date":"2018-11-19","paper":"/paper/unsupervised-domain-adaptation-an-adaptive","paper_url":"https://arxiv.org/abs/1811.07456v2","paper_title":"Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptation","code":"https://github.com/thuml/Transfer-Learning-Library","n_code_links":3,"syntology":null},{"rank_in_archive_order":26,"model":"CDAN","metrics":{"Accuracy":"73.7"},"uses_additional_data":false,"paper_date":"2017-05-26","paper":"/paper/conditional-adversarial-domain-adaptation","paper_url":"http://arxiv.org/abs/1705.10667v4","paper_title":"Conditional Adversarial Domain Adaptation","code":"https://github.com/thuml/Transfer-Learning-Library","n_code_links":5,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":27,"model":"DeepJDOT","metrics":{"Accuracy":"66.9"},"uses_additional_data":false,"paper_date":"2018-03-27","paper":"/paper/deepjdot-deep-joint-distribution-optimal","paper_url":"http://arxiv.org/abs/1803.10081v3","paper_title":"DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation","code":"https://github.com/bbdamodaran/deepJDOT","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":17,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":28,"model":"JAN","metrics":{"Accuracy":"58.3"},"uses_additional_data":false,"paper_date":"2016-05-21","paper":"/paper/deep-transfer-learning-with-joint-adaptation","paper_url":"http://arxiv.org/abs/1605.06636v2","paper_title":"Deep Transfer Learning with Joint Adaptation Networks","code":"https://github.com/thuml/Transfer-Learning-Library","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 6,264 of the 9,581 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":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+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":11,"rows_with_any_sample_ran":8,"distinct_papers_with_graph_line":9,"distinct_papers_with_any_sample_ran":6,"samples_over_distinct_papers":{"n_ran":9,"n_unverified":33,"n_samples":42,"n_pointer_only_licence":10,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":11,"n_unverified":37,"n_samples":48,"n_pointer_only_licence":16,"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"}}}