{"url":"/sota/domain-adaptation-on-mnist-to-usps","task":{"name":"Domain Adaptation","url":"/task/domain-adaptation","note":null},"dataset":{"name":"MNIST-to-USPS","url":"/dataset/mnist"},"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":14,"rows_with_code":13,"rows_with_paper_page":14,"rows_dated":14,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"FACT","metrics":{"Accuracy":"98.8"},"uses_additional_data":false,"paper_date":"2023-06-01","paper":"/paper/fact-federated-adversarial-cross-training","paper_url":"https://arxiv.org/abs/2306.00607v2","paper_title":"FACT: Federated Adversarial Cross Training","code":"https://github.com/jonas-lippl/fact","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"FAMCD","metrics":{"Accuracy":"98.72"},"uses_additional_data":false,"paper_date":"2022-10-03","paper":"/paper/unsupervised-domain-adaptation-using-feature-2","paper_url":"https://doi.org/10.1117/12.2646422","paper_title":"Unsupervised domain adaptation using feature aligned maximum classifier discrepancy","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"DFA-MCD","metrics":{"Accuracy":"98.6"},"uses_additional_data":false,"paper_date":"2020-06-23","paper":"/paper/discriminative-feature-alignment","paper_url":"https://arxiv.org/abs/2006.12770v5","paper_title":"Discriminative Feature Alignment: Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent Alignment","code":"https://github.com/JingWang18/Discriminative-Feature-Alignment","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"Mean teacher","metrics":{"Accuracy":"98.26"},"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":5,"model":"DRANet","metrics":{"Accuracy":"98.2"},"uses_additional_data":false,"paper_date":"2021-03-24","paper":"/paper/dranet-disentangling-representation-and","paper_url":"https://arxiv.org/abs/2103.13447v2","paper_title":"DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation","code":"https://github.com/Seung-Hun-Lee/DRANet","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":6,"model":"SHOT","metrics":{"Accuracy":"98.0"},"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":7,"model":"DFA-ENT","metrics":{"Accuracy":"97.9"},"uses_additional_data":false,"paper_date":"2020-06-23","paper":"/paper/discriminative-feature-alignment","paper_url":"https://arxiv.org/abs/2006.12770v5","paper_title":"Discriminative Feature Alignment: Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent Alignment","code":"https://github.com/JingWang18/Discriminative-Feature-Alignment","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":"CyCleGAN (Light-weight Calibrator)","metrics":{"Accuracy":"97.1"},"uses_additional_data":false,"paper_date":"2019-11-28","paper":"/paper/light-weight-calibrator-a-separable-component","paper_url":"https://arxiv.org/abs/1911.12796v2","paper_title":"Light-weight Calibrator: a Separable Component for Unsupervised Domain Adaptation","code":"https://github.com/yeshaokai/Calibrator-Domain-Adaptation","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"3CATN","metrics":{"Accuracy":"96.1"},"uses_additional_data":false,"paper_date":"2019-09-17","paper":"/paper/cycle-consistent-conditional-adversarial","paper_url":"https://arxiv.org/abs/1909.07618v1","paper_title":"Cycle-consistent Conditional Adversarial Transfer Networks","code":"https://github.com/lijin118/3CATN","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"rRevGrad+CAT","metrics":{"Accuracy":"96"},"uses_additional_data":false,"paper_date":"2019-03-24","paper":"/paper/cluster-alignment-with-a-teacher-for","paper_url":"https://arxiv.org/abs/1903.09980v2","paper_title":"Cluster Alignment with a Teacher for Unsupervised Domain Adaptation","code":"https://github.com/thudzj/CAT","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"DeepJDOT","metrics":{"Accuracy":"95.7"},"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":12,"model":"SRDA (RAN)","metrics":{"Accuracy":"94.76"},"uses_additional_data":false,"paper_date":"2019-05-26","paper":"/paper/190510748","paper_url":"https://arxiv.org/abs/1905.10748v4","paper_title":"Learning Smooth Representation for Unsupervised Domain Adaptation","code":"https://github.com/CuthbertCai/SRDA","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"MCD","metrics":{"Accuracy":"93.8"},"uses_additional_data":false,"paper_date":"2017-12-07","paper":"/paper/maximum-classifier-discrepancy-for","paper_url":"http://arxiv.org/abs/1712.02560v4","paper_title":"Maximum Classifier Discrepancy for Unsupervised Domain Adaptation","code":"https://github.com/thuml/Transfer-Learning-Library","n_code_links":9,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":14,"model":"ADDN","metrics":{"Accuracy":"90.1"},"uses_additional_data":false,"paper_date":"2017-02-17","paper":"/paper/adversarial-discriminative-domain-adaptation","paper_url":"http://arxiv.org/abs/1702.05464v1","paper_title":"Adversarial Discriminative Domain Adaptation","code":"https://github.com/thuml/Transfer-Learning-Library","n_code_links":20,"syntology":{"n_ran":14,"n_unverified":34,"n_samples":48,"n_pointer_only_licence":12}}],"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":8,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":7,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":18,"n_unverified":53,"n_samples":71,"n_pointer_only_licence":16,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":18,"n_unverified":54,"n_samples":72,"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"}}}