{"url":"/sota/domain-generalization-on-gta-to-avg","task":{"name":"Domain Generalization","url":"/task/domain-generalization","note":null},"dataset":{"name":"GTA-to-Avg(Cityscapes,BDD,Mapillary)","url":null},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"The idea of **Domain Generalization** is to learn from one or multiple training domains, to extract a domain-agnostic model which can be applied to an unseen domain\n\n\n<span class=\"description-source\">Source: [Diagram Image Retrieval using Sketch-Based Deep Learning and Transfer Learning ](https://arxiv.org/abs/2004.10780)</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":24,"rows_with_code":21,"rows_with_paper_page":24,"rows_dated":24,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"SoRA","metrics":{"mIoU":"68.27"},"uses_additional_data":false,"paper_date":"2024-12-05","paper":"/paper/sora-singular-value-decomposed-low-rank","paper_url":"https://arxiv.org/abs/2412.04077v1","paper_title":"SoRA: Singular Value Decomposed Low-Rank Adaptation for Domain Generalizable Representation Learning","code":"https://github.com/ysj9909/DG-SoRA","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"MFuser","metrics":{"mIoU":"68.20"},"uses_additional_data":false,"paper_date":"2025-04-04","paper":"/paper/mamba-as-a-bridge-where-vision-foundation","paper_url":"https://arxiv.org/abs/2504.03193v1","paper_title":"Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentation","code":"https://github.com/devinxzhang/mfuser","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"tqdm (EVA02-CLIP-L)","metrics":{"mIoU":"66.05"},"uses_additional_data":false,"paper_date":"2024-07-12","paper":"/paper/textual-query-driven-mask-transformer-for","paper_url":"https://arxiv.org/abs/2407.09033v1","paper_title":"Textual Query-Driven Mask Transformer for Domain Generalized Segmentation","code":"https://github.com/ByeongHyunPak/tqdm","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"ADSI","metrics":{"mIoU":"65.57"},"uses_additional_data":false,"paper_date":"2025-04-09","paper":"/paper/domain-generalization-through-attenuation-of","paper_url":"https://arxiv.org/abs/2504.06781v1","paper_title":"Domain Generalization through Attenuation of Domain-Specific Information","code":"https://github.com/ReijiSoftmaxSaito/ADSI","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"Rein","metrics":{"mIoU":"64.3"},"uses_additional_data":false,"paper_date":"2023-12-07","paper":"/paper/stronger-fewer-superior-harnessing-vision","paper_url":"https://arxiv.org/abs/2312.04265v5","paper_title":"Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation","code":"https://github.com/w1oves/rein","n_code_links":2,"syntology":null},{"rank_in_archive_order":6,"model":"VLTSeg","metrics":{"mIoU":"63.5"},"uses_additional_data":false,"paper_date":"2023-12-04","paper":"/paper/vltseg-simple-transfer-of-clip-based-vision","paper_url":"https://arxiv.org/abs/2312.02021v4","paper_title":"Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learning","code":"https://github.com/VLTSeg/VLTSeg","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"CLOUDS","metrics":{"mIoU":"61.5"},"uses_additional_data":false,"paper_date":"2023-12-15","paper":"/paper/collaborating-foundation-models-for-domain","paper_url":"https://arxiv.org/abs/2312.09788v2","paper_title":"Collaborating Foundation Models for Domain Generalized Semantic Segmentation","code":"https://github.com/yasserben/clouds","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"DIDEX","metrics":{"mIoU":"59.7"},"uses_additional_data":false,"paper_date":"2023-12-04","paper":"/paper/generalization-by-adaptation-diffusion-based","paper_url":"https://arxiv.org/abs/2312.01850v1","paper_title":"Generalization by Adaptation: Diffusion-Based Domain Extension for Domain-Generalized Semantic Segmentation","code":"https://github.com/jniemeijer/didex","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"DGInStyle","metrics":{"mIoU":"57.78"},"uses_additional_data":false,"paper_date":"2023-12-05","paper":"/paper/dginstyle-domain-generalizable-semantic","paper_url":"https://arxiv.org/abs/2312.03048v2","paper_title":"DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"DIFF","metrics":{"mIoU":"57.15"},"uses_additional_data":false,"paper_date":"2024-06-02","paper":"/paper/diffusion-features-to-bridge-domain-gap-for","paper_url":"https://arxiv.org/abs/2406.00777v2","paper_title":"Diffusion Features to Bridge Domain Gap for Semantic Segmentation","code":"https://github.com/Yux1angJi/DIFF","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":11,"model":"HRDA","metrics":{"mIoU":"55.9"},"uses_additional_data":false,"paper_date":"2023-04-26","paper":"/paper/domain-adaptive-and-generalizable-network","paper_url":"https://arxiv.org/abs/2304.13615v2","paper_title":"Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentation","code":"https://github.com/lhoyer/DAFormer","n_code_links":3,"syntology":null},{"rank_in_archive_order":12,"model":"DAFormer","metrics":{"mIoU":"51.73"},"uses_additional_data":false,"paper_date":"2023-04-26","paper":"/paper/domain-adaptive-and-generalizable-network","paper_url":"https://arxiv.org/abs/2304.13615v2","paper_title":"Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentation","code":"https://github.com/lhoyer/DAFormer","n_code_links":3,"syntology":null},{"rank_in_archive_order":13,"model":"CMFormer","metrics":{"mIoU":"51.10"},"uses_additional_data":false,"paper_date":"2023-07-01","paper":"/paper/learning-content-enhanced-mask-transformer","paper_url":"https://arxiv.org/abs/2307.00371v5","paper_title":"Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentation","code":"https://github.com/BiQiWHU/CMFormer","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"ReVT","metrics":{"mIoU":"50.2"},"uses_additional_data":false,"paper_date":"2023-08-25","paper":"/paper/a-re-parameterized-vision-transformer-revt","paper_url":"https://arxiv.org/abs/2308.13331v1","paper_title":"A Re-Parameterized Vision Transformer (ReVT) for Domain-Generalized Semantic Segmentation","code":"https://github.com/ifnspaml/revt","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"TLDR","metrics":{"mIoU":"47.09"},"uses_additional_data":false,"paper_date":"2023-03-21","paper":"/paper/texture-learning-domain-randomization-for","paper_url":"https://arxiv.org/abs/2303.11546v2","paper_title":"Texture Learning Domain Randomization for Domain Generalized Segmentation","code":"https://github.com/ssssshwan/tldr","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"SHADE","metrics":{"mIoU":"45.27"},"uses_additional_data":false,"paper_date":"2022-04-06","paper":"/paper/style-hallucinated-dual-consistency-learning","paper_url":"https://arxiv.org/abs/2204.02548v2","paper_title":"Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation","code":"https://github.com/helioszhao/shade","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":1}},{"rank_in_archive_order":17,"model":"SAN-SAW","metrics":{"mIoU":"42.43"},"uses_additional_data":false,"paper_date":"2022-04-02","paper":"/paper/semantic-aware-domain-generalized","paper_url":"https://arxiv.org/abs/2204.00822v1","paper_title":"Semantic-Aware Domain Generalized Segmentation","code":"https://github.com/leolyj/san-saw","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"AdvStyle","metrics":{"mIoU":"42.42"},"uses_additional_data":false,"paper_date":"2022-07-11","paper":"/paper/adversarial-style-augmentation-for-domain-1","paper_url":"https://arxiv.org/abs/2207.04892v2","paper_title":"Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation","code":"https://github.com/harisankar95/AdvStyle","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"GTR","metrics":{"mIoU":"40.8"},"uses_additional_data":false,"paper_date":"2021-08-05","paper":"/paper/global-and-local-texture-randomization-for","paper_url":"https://arxiv.org/abs/2108.02376v2","paper_title":"Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":20,"model":"DRPC","metrics":{"mIoU":"39.77"},"uses_additional_data":false,"paper_date":"2019-09-02","paper":"/paper/domain-randomization-and-pyramid-consistency","paper_url":"https://arxiv.org/abs/1909.00889v2","paper_title":"Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"RobustNet","metrics":{"mIoU":"37.37"},"uses_additional_data":false,"paper_date":"2021-03-29","paper":"/paper/robustnet-improving-domain-generalization-in","paper_url":"https://arxiv.org/abs/2103.15597v2","paper_title":"RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening","code":"https://github.com/shachoi/RobustNet","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"IBN","metrics":{"mIoU":"34.63"},"uses_additional_data":false,"paper_date":"2018-07-25","paper":"/paper/two-at-once-enhancing-learning-and","paper_url":"https://arxiv.org/abs/1807.09441v3","paper_title":"Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net","code":"https://github.com/layumi/Person_reID_baseline_pytorch","n_code_links":25,"syntology":{"n_ran":4,"n_unverified":12,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":23,"model":"Self-adaptation (ResNet - 50)","metrics":{"mIoU":"44,07"},"uses_additional_data":false,"paper_date":"2022-08-10","paper":"/paper/semantic-self-adaptation-enhancing","paper_url":"https://arxiv.org/abs/2208.05788v3","paper_title":"Semantic Self-adaptation: Enhancing Generalization with a Single Sample","code":"https://github.com/visinf/self-adaptive","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"Self-adaptation (ResNet - 101)","metrics":{"mIoU":"44,89"},"uses_additional_data":false,"paper_date":"2022-08-10","paper":"/paper/semantic-self-adaptation-enhancing","paper_url":"https://arxiv.org/abs/2208.05788v3","paper_title":"Semantic Self-adaptation: Enhancing Generalization with a Single Sample","code":"https://github.com/visinf/self-adaptive","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 6,885 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":7,"distinct_papers_with_any_sample_ran":7,"samples_over_distinct_papers":{"n_ran":15,"n_unverified":23,"n_samples":38,"n_pointer_only_licence":4,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":15,"n_unverified":23,"n_samples":38,"n_pointer_only_licence":4,"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"}}}