{"url":"/sota/unsupervised-domain-adaptation-on-gtav-to","task":{"name":"Unsupervised Domain Adaptation","url":"/task/unsupervised-domain-adaptation","note":null},"dataset":{"name":"GTAV-to-Cityscapes Labels","url":"/dataset/gta5"},"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":["mIoU"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"mIoU":null}},"counts":{"rows":20,"rows_with_code":18,"rows_with_paper_page":20,"rows_dated":20,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"MIC","metrics":{"mIoU":"75.9"},"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":2,"model":"HRDA + PiPa","metrics":{"mIoU":"75.6"},"uses_additional_data":false,"paper_date":"2022-11-14","paper":"/paper/pipa-pixel-and-patch-wise-self-supervised","paper_url":"https://arxiv.org/abs/2211.07609v1","paper_title":"PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation","code":"https://github.com/chen742/PiPa","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"CLUDA+HRDA","metrics":{"mIoU":"74.4"},"uses_additional_data":false,"paper_date":"2022-08-27","paper":"/paper/cluda-contrastive-learning-in-unsupervised","paper_url":"https://arxiv.org/abs/2208.14227v2","paper_title":"CLUDA : Contrastive Learning in Unsupervised Domain Adaptation for Semantic Segmentation","code":"https://github.com/user0407/CLUDA","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"HRDA","metrics":{"mIoU":"73.8"},"uses_additional_data":false,"paper_date":"2022-04-27","paper":"/paper/hrda-context-aware-high-resolution-domain","paper_url":"https://arxiv.org/abs/2204.13132v2","paper_title":"HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation","code":"https://github.com/lhoyer/hrda","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"DAFormer + PiPa","metrics":{"mIoU":"71.7"},"uses_additional_data":false,"paper_date":"2022-11-14","paper":"/paper/pipa-pixel-and-patch-wise-self-supervised","paper_url":"https://arxiv.org/abs/2211.07609v1","paper_title":"PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation","code":"https://github.com/chen742/PiPa","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"DIDA","metrics":{"mIoU":"71.0"},"uses_additional_data":false,"paper_date":"2023-07-16","paper":"/paper/dual-level-interaction-for-domain-adaptive","paper_url":"https://arxiv.org/abs/2307.07972v2","paper_title":"Dual-level Interaction for Domain Adaptive Semantic Segmentation","code":"https://github.com/rainjamesy/dida","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"SePiCo","metrics":{"mIoU":"70.3"},"uses_additional_data":false,"paper_date":"2022-04-19","paper":"/paper/sepico-semantic-guided-pixel-contrast-for","paper_url":"https://arxiv.org/abs/2204.08808v2","paper_title":"SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation","code":"https://github.com/bit-da/sepico","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":8,"model":"CAMix (w DAFormer)","metrics":{"mIoU":"70.0"},"uses_additional_data":false,"paper_date":"2021-08-08","paper":"/paper/context-aware-mixup-for-domain-adaptive","paper_url":"https://arxiv.org/abs/2108.03557v3","paper_title":"Context-Aware Mixup for Domain Adaptive Semantic Segmentation","code":"https://github.com/qianyuzqy/CAMix","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":9,"model":"DAFormer + ProCST","metrics":{"mIoU":"69.4"},"uses_additional_data":true,"paper_date":"2022-04-25","paper":"/paper/procst-boosting-semantic-segmentation-using","paper_url":"https://arxiv.org/abs/2204.11891v2","paper_title":"ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer","code":"https://github.com/shahaf1313/procst","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"DAFormer","metrics":{"mIoU":"68.3"},"uses_additional_data":false,"paper_date":"2021-11-29","paper":"/paper/daformer-improving-network-architectures-and","paper_url":"https://arxiv.org/abs/2111.14887v2","paper_title":"DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation","code":"https://github.com/lhoyer/DAFormer","n_code_links":3,"syntology":{"n_ran":6,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":11,"model":"TransDA-B","metrics":{"mIoU":"63.9"},"uses_additional_data":false,"paper_date":"2022-03-15","paper":"/paper/smoothing-matters-momentum-transformer-for","paper_url":"https://arxiv.org/abs/2203.07988v1","paper_title":"Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentation","code":"https://github.com/alpc91/transda","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":6,"n_samples":8,"n_pointer_only_licence":2}},{"rank_in_archive_order":12,"model":"BiSMAP (ResNet 101)","metrics":{"mIoU":"61.2"},"uses_additional_data":false,"paper_date":"2022-04-16","paper":"/paper/bidirectional-self-training-with-multiple","paper_url":"https://arxiv.org/abs/2204.07730v2","paper_title":"Bidirectional Self-Training with Multiple Anisotropic Prototypes for Domain Adaptive Semantic Segmentation","code":"https://github.com/luyvlei/BiSMAPs","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"G2L","metrics":{"mIoU":"59.7"},"uses_additional_data":false,"paper_date":"2022-09-07","paper":"/paper/g2l-a-global-to-local-alignment-method-for","paper_url":"https://www.sciencedirect.com/science/article/pii/S1877050922012170","paper_title":"G2L: A Global to Local Alignment Method for Unsupervised Domain Adaptive Semantic Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"FAFS","metrics":{"mIoU":"58.8"},"uses_additional_data":false,"paper_date":"2022-09-13","paper":"/paper/a-novel-unsupervised-domain-adaption-method","paper_url":"https://ieeexplore.ieee.org/document/9888149","paper_title":"A Novel Unsupervised Domain Adaption Method for Depth-Guided Semantic Segmentation Using Coarse-to-Fine Alignment","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"Re-EnD-UDA","metrics":{"mIoU":"57.98"},"uses_additional_data":false,"paper_date":"2021-04-29","paper":"/paper/rethinking-ensemble-distillation-for-semantic","paper_url":"https://arxiv.org/abs/2104.14203v1","paper_title":"Rethinking Ensemble-Distillation for Semantic Segmentation Based Unsupervised Domain Adaptation","code":"https://github.com/Chao-Chen-Hao/Rethinking-EnD-SegUDA","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"CAMix (w Deeplabv2 ResNet 101)","metrics":{"mIoU":"55.2"},"uses_additional_data":false,"paper_date":"2021-08-08","paper":"/paper/context-aware-mixup-for-domain-adaptive","paper_url":"https://arxiv.org/abs/2108.03557v3","paper_title":"Context-Aware Mixup for Domain Adaptive Semantic Segmentation","code":"https://github.com/qianyuzqy/CAMix","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":17,"model":"Uncertainty + Adaboost","metrics":{"mIoU":"50.9"},"uses_additional_data":false,"paper_date":"2021-03-29","paper":"/paper/adaptive-boosting-for-domain-adaptation","paper_url":"https://arxiv.org/abs/2103.15685v3","paper_title":"Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation","code":"https://github.com/layumi/AdaBoost_Seg","n_code_links":2,"syntology":null},{"rank_in_archive_order":18,"model":"Uncertainty","metrics":{"mIoU":"50.3"},"uses_additional_data":false,"paper_date":"2020-03-08","paper":"/paper/rectifying-pseudo-label-learning-via","paper_url":"https://arxiv.org/abs/2003.03773v3","paper_title":"Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation","code":"https://github.com/layumi/Seg-Uncertainty","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":19,"model":"BiMaL","metrics":{"mIoU":"47.3"},"uses_additional_data":false,"paper_date":"2021-08-06","paper":"/paper/bimal-bijective-maximum-likelihood-approach","paper_url":"https://arxiv.org/abs/2108.03267v1","paper_title":"BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation","code":"https://github.com/uark-cviu/bimal","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"MRNet","metrics":{"mIoU":"45.5"},"uses_additional_data":false,"paper_date":"2019-12-24","paper":"/paper/unsupervised-scene-adaptation-with-memory","paper_url":"https://arxiv.org/abs/1912.11164v3","paper_title":"Unsupervised Scene Adaptation with Memory Regularization in vivo","code":"https://github.com/layumi/Seg-Uncertainty","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}}],"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 6,885 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":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"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":7,"distinct_papers_with_graph_line":6,"distinct_papers_with_any_sample_ran":6,"samples_over_distinct_papers":{"n_ran":18,"n_unverified":7,"n_samples":25,"n_pointer_only_licence":14,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":21,"n_unverified":8,"n_samples":29,"n_pointer_only_licence":15,"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"}}}