{"url":"/sota/single-source-domain-generalization-on-pacs","task":{"name":"Single-Source Domain Generalization","url":"/task/single-source-domain-generalization","note":null},"dataset":{"name":"PACS","url":"/dataset/pacs"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"In this task a model is trained in a single source domain and then it is tested in a number of target domains","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":10,"rows_with_code":7,"rows_with_paper_page":10,"rows_dated":10,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Crafting-Shifts(ResNet18)","metrics":{"Accuracy":"70.37"},"uses_additional_data":false,"paper_date":"2024-09-29","paper":"/paper/crafting-distribution-shifts-for-validation","paper_url":"https://arxiv.org/abs/2409.19774v1","paper_title":"Crafting Distribution Shifts for Validation and Training in Single Source Domain Generalization","code":"https://github.com/nikosefth/crafting-shifts","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"MCL (ResNet18)","metrics":{"Accuracy":"69.86"},"uses_additional_data":false,"paper_date":"2023-04-07","paper":"/paper/meta-causal-learning-for-single-domain","paper_url":"https://arxiv.org/abs/2304.03709v1","paper_title":"Meta-causal Learning for Single Domain Generalization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"ProRandConv (ResNet18)","metrics":{"Accuracy":"68.88"},"uses_additional_data":false,"paper_date":"2023-04-02","paper":"/paper/progressive-random-convolutions-for-single","paper_url":"https://arxiv.org/abs/2304.00424v1","paper_title":"Progressive Random Convolutions for Single Domain Generalization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"CADA (ResNet18)","metrics":{"Accuracy":"68.41"},"uses_additional_data":false,"paper_date":"2023-01-01","paper":"/paper/center-aware-adversarial-augmentation-for","paper_url":"https://ieeexplore.ieee.org/document/10031006","paper_title":"Center-aware Adversarial Augmentation for Single Domain Generalization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"ITTA (ResNet18)","metrics":{"Accuracy":"68.4"},"uses_additional_data":false,"paper_date":"2023-04-10","paper":"/paper/improved-test-time-adaptation-for-domain","paper_url":"https://arxiv.org/abs/2304.04494v2","paper_title":"Improved Test-Time Adaptation for Domain Generalization","code":"https://github.com/liangchen527/itta","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":6,"model":"XDED (ResNet18)","metrics":{"Accuracy":"66.5"},"uses_additional_data":false,"paper_date":"2022-11-25","paper":"/paper/cross-domain-ensemble-distillation-for-domain-2","paper_url":"https://arxiv.org/abs/2211.14058v1","paper_title":"Cross-Domain Ensemble Distillation for Domain Generalization","code":"https://github.com/leekyungmoon/XDED","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"ABA (ResNet18)","metrics":{"Accuracy":"66.36"},"uses_additional_data":false,"paper_date":"2023-07-18","paper":"/paper/adversarial-bayesian-augmentation-for-single","paper_url":"https://arxiv.org/abs/2307.09520v2","paper_title":"Adversarial Bayesian Augmentation for Single-Source Domain Generalization","code":"https://github.com/shengcheng/aba","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":8,"model":"GeoTexAug (ResNet18)","metrics":{"Accuracy":"65.0"},"uses_additional_data":false,"paper_date":"2022-01-01","paper":"/paper/geometric-and-textural-augmentation-for","paper_url":"http://openaccess.thecvf.com//content/CVPR2022/html/Liu_Geometric_and_Textural_Augmentation_for_Domain_Gap_Reduction_CVPR_2022_paper.html","paper_title":"Geometric and Textural Augmentation for Domain Gap Reduction","code":"https://github.com/xch-liu/geom-tex-dg","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"SagNet (ResNet18)","metrics":{"Accuracy":"61.9"},"uses_additional_data":false,"paper_date":"2019-10-25","paper":"/paper/reducing-domain-gap-via-style-agnostic","paper_url":"https://arxiv.org/abs/1910.11645v4","paper_title":"Reducing Domain Gap by Reducing Style Bias","code":"https://github.com/facebookresearch/DomainBed","n_code_links":3,"syntology":null},{"rank_in_archive_order":10,"model":"SelfReg (ResNet18)","metrics":{"Accuracy":"59.59"},"uses_additional_data":false,"paper_date":"2021-04-20","paper":"/paper/selfreg-self-supervised-contrastive","paper_url":"https://arxiv.org/abs/2104.09841v1","paper_title":"SelfReg: Self-supervised Contrastive Regularization for Domain Generalization","code":"https://github.com/facebookresearch/DomainBed","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"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":3,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":6,"n_unverified":7,"n_samples":13,"n_pointer_only_licence":6,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":6,"n_unverified":7,"n_samples":13,"n_pointer_only_licence":6,"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"}}}