{"url":"/sota/domain-generalization-on-pacs-2","task":{"name":"Domain Generalization","url":"/task/domain-generalization","note":null},"dataset":{"name":"PACS","url":"/dataset/pacs"},"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":["Average Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Average Accuracy":"higher"}},"counts":{"rows":133,"rows_with_code":96,"rows_with_paper_page":132,"rows_dated":132,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"SIMPLE+","metrics":{"Average Accuracy":"99.0"},"uses_additional_data":false,"paper_date":"2023-05-01","paper":"/paper/simple-specialized-model-sample-matching-for","paper_url":"https://openreview.net/forum?id=BqrPeZ_e5P","paper_title":"SIMPLE: Specialized Model-Sample Matching for Domain Generalization","code":"https://github.com/microsoft/SeqML/tree/main/SIMPLE","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"PromptStyler (CLIP, ViT-L/14)","metrics":{"Average Accuracy":"98.6"},"uses_additional_data":false,"paper_date":"2023-07-27","paper":"/paper/promptstyler-prompt-driven-style-generation","paper_url":"https://arxiv.org/abs/2307.15199v2","paper_title":"PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization","code":"https://github.com/zhanghr2001/promptta","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"GMDG (RegNetY-16GF, SWAD)","metrics":{"Average Accuracy":"97.9"},"uses_additional_data":false,"paper_date":"2024-02-29","paper":"/paper/rethinking-multi-domain-generalization-with-a","paper_url":"https://arxiv.org/abs/2402.18853v2","paper_title":"Rethinking Multi-domain Generalization with A General Learning Objective","code":"https://github.com/zhaorui-tan/gmdg","n_code_links":2,"syntology":null},{"rank_in_archive_order":4,"model":"D-Triplet(RegNetY-16GF)","metrics":{"Average Accuracy":"97.6"},"uses_additional_data":false,"paper_date":"2023-03-01","paper":"/paper/domain-aware-triplet-loss-in-domain","paper_url":"https://arxiv.org/abs/2303.01233v1","paper_title":"Domain-aware Triplet loss in Domain Generalization","code":"https://github.com/workerbcd/dct","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":5,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"MoA (OpenCLIP, ViT-B/16)","metrics":{"Average Accuracy":"97.4"},"uses_additional_data":false,"paper_date":"2023-10-17","paper":"/paper/domain-generalization-using-large-pretrained","paper_url":"https://arxiv.org/abs/2310.11031v2","paper_title":"Domain Generalization Using Large Pretrained Models with Mixture-of-Adapters","code":"https://github.com/KU-CVLAB/MoA","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"GMDG (e RegNetY-16GF)","metrics":{"Average Accuracy":"97.3"},"uses_additional_data":false,"paper_date":"2024-02-29","paper":"/paper/rethinking-multi-domain-generalization-with-a","paper_url":"https://arxiv.org/abs/2402.18853v2","paper_title":"Rethinking Multi-domain Generalization with A General Learning Objective","code":"https://github.com/zhaorui-tan/gmdg","n_code_links":2,"syntology":null},{"rank_in_archive_order":7,"model":"PromptStyler (CLIP, ViT-B/16)","metrics":{"Average Accuracy":"97.2"},"uses_additional_data":false,"paper_date":"2023-07-27","paper":"/paper/promptstyler-prompt-driven-style-generation","paper_url":"https://arxiv.org/abs/2307.15199v2","paper_title":"PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization","code":"https://github.com/zhanghr2001/promptta","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":"SPG (CLIP, ViT-B/16)","metrics":{"Average Accuracy":"97.0"},"uses_additional_data":false,"paper_date":"2024-04-30","paper":"/paper/soft-prompt-generation-for-domain","paper_url":"https://arxiv.org/abs/2404.19286v2","paper_title":"Soft Prompt Generation for Domain Generalization","code":"https://github.com/renytek13/soft-prompt-generation-with-cgan","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":3,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"MIRO (RegNetY-16GF, SWAD)","metrics":{"Average Accuracy":"96.8"},"uses_additional_data":false,"paper_date":"2022-03-21","paper":"/paper/domain-generalization-by-mutual-information","paper_url":"https://arxiv.org/abs/2203.10789v2","paper_title":"Domain Generalization by Mutual-Information Regularization with Pre-trained Models","code":"https://github.com/kakaobrain/miro","n_code_links":1,"syntology":{"n_ran":11,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"CAR-FT (CLIP, ViT-B/16)","metrics":{"Average Accuracy":"96.8"},"uses_additional_data":false,"paper_date":"2022-11-29","paper":"/paper/context-aware-robust-fine-tuning","paper_url":"https://arxiv.org/abs/2211.16175v1","paper_title":"Context-Aware Robust Fine-Tuning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"VL2V-SD (CLIP, ViT-B/16)","metrics":{"Average Accuracy":"96.68"},"uses_additional_data":false,"paper_date":"2023-10-12","paper":"/paper/distilling-from-vision-language-models-for","paper_url":"https://arxiv.org/abs/2310.08255v2","paper_title":"Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification","code":"https://github.com/val-iisc/VL2V-ADiP","n_code_links":1,"syntology":{"n_ran":12,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"SEDGE+","metrics":{"Average Accuracy":"96.1"},"uses_additional_data":false,"paper_date":"2022-03-09","paper":"/paper/domain-generalization-using-pretrained-models","paper_url":"https://arxiv.org/abs/2203.04600v1","paper_title":"Domain Generalization using Pretrained Models without Fine-tuning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"Ensemble of Averages (RegNetY-16GF)","metrics":{"Average Accuracy":"95.8"},"uses_additional_data":false,"paper_date":"2021-10-21","paper":"/paper/ensemble-of-averages-improving-model","paper_url":"https://arxiv.org/abs/2110.10832v4","paper_title":"Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization","code":"https://github.com/salesforce/ensemble-of-averages","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":14,"model":"UniDG + CORAL + ConvNeXt-B","metrics":{"Average Accuracy":"95.6"},"uses_additional_data":false,"paper_date":"2023-10-16","paper":"/paper/towards-unified-and-effective-domain","paper_url":"https://arxiv.org/abs/2310.10008v1","paper_title":"Towards Unified and Effective Domain Generalization","code":"https://github.com/invictus717/UniDG","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"CADG","metrics":{"Average Accuracy":"94.6"},"uses_additional_data":false,"paper_date":"2022-03-31","paper":"/paper/cadg-a-model-based-on-cross-attention-for","paper_url":"https://arxiv.org/abs/2203.17067v3","paper_title":"CADG: A Model Based on Cross Attention for Domain Generalization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"Ensemble of Averages (ResNeXt-50 32x4d)","metrics":{"Average Accuracy":"93.2"},"uses_additional_data":false,"paper_date":"2021-10-21","paper":"/paper/ensemble-of-averages-improving-model","paper_url":"https://arxiv.org/abs/2110.10832v4","paper_title":"Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization","code":"https://github.com/salesforce/ensemble-of-averages","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":17,"model":"PromptStyler (CLIP, ResNet-50)","metrics":{"Average Accuracy":"93.2"},"uses_additional_data":false,"paper_date":"2023-07-27","paper":"/paper/promptstyler-prompt-driven-style-generation","paper_url":"https://arxiv.org/abs/2307.15199v2","paper_title":"PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization","code":"https://github.com/zhanghr2001/promptta","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"SPG (CLIP, ResNet-50)","metrics":{"Average Accuracy":"92.8"},"uses_additional_data":false,"paper_date":"2024-04-30","paper":"/paper/soft-prompt-generation-for-domain","paper_url":"https://arxiv.org/abs/2404.19286v2","paper_title":"Soft Prompt Generation for Domain Generalization","code":"https://github.com/renytek13/soft-prompt-generation-with-cgan","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":3,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"EoQ (ResNet-50)","metrics":{"Average Accuracy":"90.7"},"uses_additional_data":false,"paper_date":"2024-10-08","paper":"/paper/qt-dog-quantization-aware-training-for-domain","paper_url":"https://arxiv.org/abs/2410.06020v1","paper_title":"QT-DoG: Quantization-aware Training for Domain Generalization","code":"https://github.com/saqibjaved1/QT-DoG","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":20,"model":"Model Ratatouille","metrics":{"Average Accuracy":"90.5"},"uses_additional_data":false,"paper_date":"2022-12-20","paper":"/paper/recycling-diverse-models-for-out-of","paper_url":"https://arxiv.org/abs/2212.10445v3","paper_title":"Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization","code":"https://github.com/facebookresearch/ModelRatatouille","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"RISE (ResNet-50)","metrics":{"Average Accuracy":"90.2"},"uses_additional_data":false,"paper_date":"2023-09-21","paper":"/paper/a-sentence-speaks-a-thousand-images-domain","paper_url":"https://arxiv.org/abs/2309.12530v1","paper_title":"A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance","code":"https://github.com/oodbag/rise","n_code_links":1,"syntology":{"n_ran":14,"n_unverified":2,"n_samples":16,"n_pointer_only_licence":16}},{"rank_in_archive_order":22,"model":"AdaClust (ResNet-50, SWAD)","metrics":{"Average Accuracy":"89.2"},"uses_additional_data":false,"paper_date":"2021-12-09","paper":"/paper/adaptive-methods-for-aggregated-domain","paper_url":"https://arxiv.org/abs/2112.04766v2","paper_title":"Adaptive Methods for Aggregated Domain Generalization","code":"https://github.com/xavierohan/AdaClust_DomainBed","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"PCL (ResNet50, SWAD)","metrics":{"Average Accuracy":"88.7"},"uses_additional_data":false,"paper_date":"2022-01-01","paper":"/paper/pcl-proxy-based-contrastive-learning-for","paper_url":"http://openaccess.thecvf.com//content/CVPR2022/html/Yao_PCL_Proxy-Based_Contrastive_Learning_for_Domain_Generalization_CVPR_2022_paper.html","paper_title":"PCL: Proxy-Based Contrastive Learning for Domain Generalization","code":"https://github.com/yaoxufeng/PCL-Proxy-based-Contrastive-Learning-for-Domain-Generalization","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"LRDG (ResNet-50)","metrics":{"Average Accuracy":"88.63"},"uses_additional_data":false,"paper_date":"2022-12-14","paper":"/paper/domain-generalization-by-learning-and","paper_url":"https://arxiv.org/abs/2212.07101v1","paper_title":"Domain Generalization by Learning and Removing Domain-specific Features","code":"https://github.com/yulearningg/LRDG","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":25,"model":"Ensemble of Averages (ResNet-50)","metrics":{"Average Accuracy":"88.6"},"uses_additional_data":false,"paper_date":"2021-10-21","paper":"/paper/ensemble-of-averages-improving-model","paper_url":"https://arxiv.org/abs/2110.10832v4","paper_title":"Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization","code":"https://github.com/salesforce/ensemble-of-averages","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":26,"model":"BatchFormer(ResNet-50, SWAD)","metrics":{"Average Accuracy":"88.6"},"uses_additional_data":false,"paper_date":"2022-03-03","paper":"/paper/batchformer-learning-to-explore-sample","paper_url":"https://arxiv.org/abs/2203.01522v2","paper_title":"BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning","code":"https://github.com/zhihou7/batchformer","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":27,"model":"SIMPLE","metrics":{"Average Accuracy":"88.6"},"uses_additional_data":false,"paper_date":"2023-05-01","paper":"/paper/simple-specialized-model-sample-matching-for","paper_url":"https://openreview.net/forum?id=BqrPeZ_e5P","paper_title":"SIMPLE: Specialized Model-Sample Matching for Domain Generalization","code":"https://github.com/microsoft/SeqML/tree/main/SIMPLE","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"MIRO (ResNet-50, SWAD)","metrics":{"Average Accuracy":"88.4"},"uses_additional_data":false,"paper_date":"2022-03-21","paper":"/paper/domain-generalization-by-mutual-information","paper_url":"https://arxiv.org/abs/2203.10789v2","paper_title":"Domain Generalization by Mutual-Information Regularization with Pre-trained Models","code":"https://github.com/kakaobrain/miro","n_code_links":1,"syntology":{"n_ran":11,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":29,"model":"GMDG (ResNet-50, SWAD)","metrics":{"Average Accuracy":"88.4"},"uses_additional_data":false,"paper_date":"2024-02-29","paper":"/paper/rethinking-multi-domain-generalization-with-a","paper_url":"https://arxiv.org/abs/2402.18853v2","paper_title":"Rethinking Multi-domain Generalization with A General Learning Objective","code":"https://github.com/zhaorui-tan/gmdg","n_code_links":2,"syntology":null},{"rank_in_archive_order":30,"model":"VNE (ResNet-50, SWAD)","metrics":{"Average Accuracy":"88.3"},"uses_additional_data":false,"paper_date":"2023-04-04","paper":"/paper/vne-an-effective-method-for-improving-deep","paper_url":"https://arxiv.org/abs/2304.01434v1","paper_title":"VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution","code":"https://github.com/jaeill/CVPR23-VNE","n_code_links":1,"syntology":null},{"rank_in_archive_order":31,"model":"SWAD (ResNet-50)","metrics":{"Average Accuracy":"88.1"},"uses_additional_data":false,"paper_date":"2021-02-17","paper":"/paper/domain-generalization-needs-stochastic-weight","paper_url":"https://arxiv.org/abs/2102.08604v4","paper_title":"SWAD: Domain Generalization by Seeking Flat Minima","code":"https://github.com/khanrc/swad","n_code_links":4,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":32,"model":"GMoE-S/16","metrics":{"Average Accuracy":"88.1"},"uses_additional_data":false,"paper_date":"2022-06-08","paper":"/paper/sparse-fusion-mixture-of-experts-are-domain","paper_url":"https://arxiv.org/abs/2206.04046v6","paper_title":"Sparse Mixture-of-Experts are Domain Generalizable Learners","code":"https://github.com/luodian/sf-moe-dg","n_code_links":2,"syntology":{"n_ran":7,"n_unverified":7,"n_samples":14,"n_pointer_only_licence":14}},{"rank_in_archive_order":33,"model":"QT-DoG (ResNet-50)","metrics":{"Average Accuracy":"87.89"},"uses_additional_data":false,"paper_date":"2024-10-08","paper":"/paper/qt-dog-quantization-aware-training-for-domain","paper_url":"https://arxiv.org/abs/2410.06020v1","paper_title":"QT-DoG: Quantization-aware Training for Domain Generalization","code":"https://github.com/saqibjaved1/QT-DoG","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":34,"model":"DDG","metrics":{"Average Accuracy":"87.87"},"uses_additional_data":false,"paper_date":"2022-05-27","paper":"/paper/dynamic-domain-generalization","paper_url":"https://arxiv.org/abs/2205.13913v1","paper_title":"Dynamic Domain Generalization","code":"https://github.com/metavisionlab/ddg","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":35,"model":"RSC (ResNet-50)","metrics":{"Average Accuracy":"87.83"},"uses_additional_data":false,"paper_date":"2020-07-05","paper":"/paper/self-challenging-improves-cross-domain","paper_url":"https://arxiv.org/abs/2007.02454v1","paper_title":"Self-Challenging Improves Cross-Domain Generalization","code":"https://github.com/facebookresearch/DomainBed","n_code_links":8,"syntology":{"n_ran":3,"n_unverified":4,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":36,"model":"WAKD (DeiT-Ti)","metrics":{"Average Accuracy":"87.6"},"uses_additional_data":false,"paper_date":"2023-09-20","paper":"/paper/weight-averaging-improves-knowledge","paper_url":"https://arxiv.org/abs/2309.11446v1","paper_title":"Weight Averaging Improves Knowledge Distillation under Domain Shift","code":"https://github.com/vorobeevich/distillation-in-dg","n_code_links":1,"syntology":null},{"rank_in_archive_order":37,"model":"MDG-Hybrid (ResNet-50)","metrics":{"Average Accuracy":"87.52"},"uses_additional_data":false,"paper_date":"2020-06-12","paper":"/paper/domain-generalization-using-causal-matching-1","paper_url":"https://arxiv.org/abs/2006.07500v3","paper_title":"Domain Generalization using Causal Matching","code":"https://github.com/microsoft/robustdg","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":5,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":38,"model":"DREAME","metrics":{"Average Accuracy":"87.35"},"uses_additional_data":false,"paper_date":"2021-12-17","paper":"/paper/improving-multi-domain-generalization-through","paper_url":"https://arxiv.org/abs/2112.09802v3","paper_title":"Automated Domain Discovery from Multiple Sources to Improve Zero-Shot Generalization","code":"https://github.com/kowshikthopalli/DREAME","n_code_links":1,"syntology":null},{"rank_in_archive_order":39,"model":"D-Triplet(Resnet-50)","metrics":{"Average Accuracy":"87.3"},"uses_additional_data":false,"paper_date":"2023-03-01","paper":"/paper/domain-aware-triplet-loss-in-domain","paper_url":"https://arxiv.org/abs/2303.01233v1","paper_title":"Domain-aware Triplet loss in Domain Generalization","code":"https://github.com/workerbcd/dct","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":5,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":40,"model":"AdaClust (ResNet-50)","metrics":{"Average Accuracy":"87.0"},"uses_additional_data":false,"paper_date":"2021-12-09","paper":"/paper/adaptive-methods-for-aggregated-domain","paper_url":"https://arxiv.org/abs/2112.04766v2","paper_title":"Adaptive Methods for Aggregated Domain Generalization","code":"https://github.com/xavierohan/AdaClust_DomainBed","n_code_links":1,"syntology":null},{"rank_in_archive_order":41,"model":"Fishr(ResNet-50,DomainBed)","metrics":{"Average Accuracy":"86.9"},"uses_additional_data":false,"paper_date":"2021-09-07","paper":"/paper/fishr-invariant-gradient-variances-for-out-of","paper_url":"https://arxiv.org/abs/2109.02934v3","paper_title":"Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization","code":"https://github.com/facebookresearch/DomainBed","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":42,"model":"Meta-DMoE (ResNet-50)","metrics":{"Average Accuracy":"86.9"},"uses_additional_data":false,"paper_date":"2022-10-08","paper":"/paper/meta-dmoe-adapting-to-domain-shift-by-meta","paper_url":"https://arxiv.org/abs/2210.03885v2","paper_title":"Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Experts","code":"https://github.com/n3il666/meta-dmoe","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":43,"model":"POEM","metrics":{"Average Accuracy":"86.7"},"uses_additional_data":false,"paper_date":"2023-05-22","paper":"/paper/poem-polarization-of-embeddings-for-domain","paper_url":"https://arxiv.org/abs/2305.13046v1","paper_title":"POEM: Polarization of Embeddings for Domain-Invariant Representations","code":"https://github.com/josangyoung/official-poem","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":44,"model":"DSON (Resnet-50)","metrics":{"Average Accuracy":"86.64"},"uses_additional_data":false,"paper_date":"2019-07-09","paper":"/paper/learning-to-optimize-domain-specific","paper_url":"https://arxiv.org/abs/1907.04275v3","paper_title":"Learning to Optimize Domain Specific Normalization for Domain Generalization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":45,"model":"STEAM (Resnet-18)","metrics":{"Average Accuracy":"86.6"},"uses_additional_data":false,"paper_date":"2021-12-14","paper":"/paper/a-style-and-semantic-memory-mechanism-for-1","paper_url":"https://arxiv.org/abs/2112.07517v1","paper_title":"A Style and Semantic Memory Mechanism for Domain Generalization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":46,"model":"WAKD (Resnet-18)","metrics":{"Average Accuracy":"86.6"},"uses_additional_data":false,"paper_date":"2023-09-20","paper":"/paper/weight-averaging-improves-knowledge","paper_url":"https://arxiv.org/abs/2309.11446v1","paper_title":"Weight Averaging Improves Knowledge Distillation under Domain Shift","code":"https://github.com/vorobeevich/distillation-in-dg","n_code_links":1,"syntology":null},{"rank_in_archive_order":47,"model":"XDED (ResNet-18)","metrics":{"Average Accuracy":"86.4"},"uses_additional_data":false,"paper_date":"2021-09-29","paper":"/paper/cross-domain-ensemble-distillation-for-domain","paper_url":"https://openreview.net/forum?id=63PjP_UEKe","paper_title":"Cross Domain Ensemble Distillation for Domain Generalization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":48,"model":"XDED (ResNet-18)","metrics":{"Average Accuracy":"86.4"},"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":49,"model":"EISNet (Resnet-50)","metrics":{"Average Accuracy":"85.84"},"uses_additional_data":false,"paper_date":"2020-07-18","paper":"/paper/learning-from-extrinsic-and-intrinsic","paper_url":"https://arxiv.org/abs/2007.09316v1","paper_title":"Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":50,"model":"GMDG (ResNet-50)","metrics":{"Average Accuracy":"85.6"},"uses_additional_data":false,"paper_date":"2024-02-29","paper":"/paper/rethinking-multi-domain-generalization-with-a","paper_url":"https://arxiv.org/abs/2402.18853v2","paper_title":"Rethinking Multi-domain Generalization with A General Learning Objective","code":"https://github.com/zhaorui-tan/gmdg","n_code_links":2,"syntology":null},{"rank_in_archive_order":51,"model":"ERM (Resnet-50, DomainBed)","metrics":{"Average Accuracy":"85.50"},"uses_additional_data":false,"paper_date":"2020-07-02","paper":"/paper/in-search-of-lost-domain-generalization","paper_url":"https://arxiv.org/abs/2007.01434v1","paper_title":"In Search of Lost Domain Generalization","code":"https://github.com/facebookresearch/DomainBed","n_code_links":12,"syntology":{"n_ran":3,"n_unverified":4,"n_samples":7,"n_pointer_only_licence":1}},{"rank_in_archive_order":52,"model":"ER (Resnet-50)","metrics":{"Average Accuracy":"85.34"},"uses_additional_data":false,"paper_date":"2020-12-01","paper":"/paper/domain-generalization-via-entropy","paper_url":"http://proceedings.neurips.cc/paper/2020/hash/b98249b38337c5088bbc660d8f872d6a-Abstract.html","paper_title":"Domain Generalization via Entropy Regularization","code":"https://github.com/sshan-zhao/DG_via_ER","n_code_links":1,"syntology":null},{"rank_in_archive_order":53,"model":"RSC (Resnet-50, DomainBed)","metrics":{"Average Accuracy":"85.2"},"uses_additional_data":false,"paper_date":"2020-07-05","paper":"/paper/self-challenging-improves-cross-domain","paper_url":"https://arxiv.org/abs/2007.02454v1","paper_title":"Self-Challenging Improves Cross-Domain Generalization","code":"https://github.com/facebookresearch/DomainBed","n_code_links":8,"syntology":{"n_ran":3,"n_unverified":4,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":54,"model":"RSC (Resnet-18)","metrics":{"Average Accuracy":"85.15"},"uses_additional_data":false,"paper_date":"2020-07-05","paper":"/paper/self-challenging-improves-cross-domain","paper_url":"https://arxiv.org/abs/2007.02454v1","paper_title":"Self-Challenging Improves Cross-Domain Generalization","code":"https://github.com/facebookresearch/DomainBed","n_code_links":8,"syntology":{"n_ran":3,"n_unverified":4,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":55,"model":"DSON (Resnet-18)","metrics":{"Average Accuracy":"85.11"},"uses_additional_data":false,"paper_date":"2019-07-09","paper":"/paper/learning-to-optimize-domain-specific","paper_url":"https://arxiv.org/abs/1907.04275v3","paper_title":"Learning to Optimize Domain Specific Normalization for Domain Generalization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":56,"model":"StableNet (ResNet-18)","metrics":{"Average Accuracy":"84.69"},"uses_additional_data":false,"paper_date":"2021-04-16","paper":"/paper/deep-stable-learning-for-out-of-distribution","paper_url":"https://arxiv.org/abs/2104.07876v1","paper_title":"Deep Stable Learning for Out-Of-Distribution Generalization","code":"https://github.com/xxgege/StableNet","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":8,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":57,"model":"DGIS (Resnet-18, Painting)","metrics":{"Average Accuracy":"84.64"},"uses_additional_data":false,"paper_date":"2020-06-19","paper":"/paper/frustratingly-simple-domain-generalization","paper_url":"https://arxiv.org/abs/2006.11207v2","paper_title":"Frustratingly Simple Domain Generalization via Image Stylization","code":"https://github.com/GT-RIPL/DomainGeneralization-Stylization","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":58,"model":"MMD-AAE (Resnet-50, DomainBed)","metrics":{"Average Accuracy":"84.6"},"uses_additional_data":false,"paper_date":"2018-06-01","paper":"/paper/domain-generalization-with-adversarial","paper_url":"http://openaccess.thecvf.com/content_cvpr_2018/html/Li_Domain_Generalization_With_CVPR_2018_paper.html","paper_title":"Domain Generalization With Adversarial Feature Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":59,"model":"Mixup (Resnet-50, DomainBed)","metrics":{"Average Accuracy":"84.6"},"uses_additional_data":false,"paper_date":"2020-01-03","paper":"/paper/improve-unsupervised-domain-adaptation-with","paper_url":"https://arxiv.org/abs/2001.00677v1","paper_title":"Improve Unsupervised Domain Adaptation with Mixup Training","code":"https://github.com/facebookresearch/DomainBed","n_code_links":1,"syntology":null},{"rank_in_archive_order":60,"model":"DDEC (Resnet-18)","metrics":{"Average Accuracy":"84.46"},"uses_additional_data":false,"paper_date":"2019-09-18","paper":"/paper/towards-shape-biased-unsupervised","paper_url":"https://arxiv.org/abs/1909.08245v2","paper_title":"Towards Shape Biased Unsupervised Representation Learning for Domain Generalization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":61,"model":"GroupDRO (Resnet-50, DomainBed)","metrics":{"Average Accuracy":"84.4"},"uses_additional_data":false,"paper_date":"2019-11-20","paper":"/paper/distributionally-robust-neural-networks-for","paper_url":"https://arxiv.org/abs/1911.08731v2","paper_title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","code":"https://github.com/facebookresearch/DomainBed","n_code_links":8,"syntology":{"n_ran":9,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":2}},{"rank_in_archive_order":62,"model":"MDG-Hybrid (Resnet-18)","metrics":{"Average Accuracy":"84.35"},"uses_additional_data":false,"paper_date":"2020-06-12","paper":"/paper/domain-generalization-using-causal-matching-1","paper_url":"https://arxiv.org/abs/2006.07500v3","paper_title":"Domain Generalization using Causal Matching","code":"https://github.com/microsoft/robustdg","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":5,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":63,"model":"Stylized (Resnet-18)","metrics":{"Average Accuracy":"84.32"},"uses_additional_data":false,"paper_date":"2021-01-22","paper":"/paper/rethinking-domain-generalization-baselines","paper_url":"https://arxiv.org/abs/2101.09060v2","paper_title":"Rethinking Domain Generalization Baselines","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":64,"model":"NAS-OoD (R","metrics":{"Average Accuracy":"84.23"},"uses_additional_data":false,"paper_date":"2021-09-05","paper":"/paper/nas-ood-neural-architecture-search-for-out-of","paper_url":"https://arxiv.org/abs/2109.02038v1","paper_title":"NAS-OoD: Neural Architecture Search for Out-of-Distribution Generalization","code":"https://github.com/HaoyueBaiZJU/NAS-OoD","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":3,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":65,"model":"SEDGE","metrics":{"Average Accuracy":"84.1"},"uses_additional_data":false,"paper_date":"2022-03-09","paper":"/paper/domain-generalization-using-pretrained-models","paper_url":"https://arxiv.org/abs/2203.04600v1","paper_title":"Domain Generalization using Pretrained Models without Fine-tuning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":66,"model":"MixStyle (Resnet-18)","metrics":{"Average Accuracy":"83.7"},"uses_additional_data":false,"paper_date":"2021-04-05","paper":"/paper/domain-generalization-with-mixstyle-1","paper_url":"https://arxiv.org/abs/2104.02008v1","paper_title":"Domain Generalization with MixStyle","code":"https://github.com/thuml/Transfer-Learning-Library","n_code_links":3,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":67,"model":"SelfReg (Resnet-50)","metrics":{"Average Accuracy":"83.62"},"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}},{"rank_in_archive_order":68,"model":"MetaReg (Resnet-50)","metrics":{"Average Accuracy":"83.6"},"uses_additional_data":false,"paper_date":"2018-12-01","paper":"/paper/metareg-towards-domain-generalization-using","paper_url":"http://papers.nips.cc/paper/7378-metareg-towards-domain-generalization-using-meta-regularization","paper_title":"MetaReg: Towards Domain Generalization using Meta-Regularization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":69,"model":"DMG (Resnet-50)","metrics":{"Average Accuracy":"83.37"},"uses_additional_data":false,"paper_date":"2020-08-28","paper":"/paper/learning-to-balance-specificity-and","paper_url":"https://arxiv.org/abs/2008.12839v1","paper_title":"Learning to Balance Specificity and Invariance for In and Out of Domain Generalization","code":"https://github.com/prithv1/DMG","n_code_links":1,"syntology":null},{"rank_in_archive_order":70,"model":"G2DM (ResNet-18)","metrics":{"Average Accuracy":"83.34"},"uses_additional_data":false,"paper_date":"2019-11-03","paper":"/paper/adversarial-target-invariant-representation","paper_url":"https://arxiv.org/abs/1911.00804v6","paper_title":"Generalizing to unseen domains via distribution matching","code":"https://github.com/belaalb/g2dm","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":71,"model":"SagNet (Resnet-18)","metrics":{"Average Accuracy":"83.25"},"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":72,"model":"BNE (ResNet-18)","metrics":{"Average Accuracy":"83.1"},"uses_additional_data":false,"paper_date":"2020-11-25","paper":"/paper/batch-normalization-embeddings-for-deep-1","paper_url":"https://arxiv.org/abs/2011.12672v3","paper_title":"Batch Normalization Embeddings for Deep Domain Generalization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":73,"model":"DDAIG (Resnet-18)","metrics":{"Average Accuracy":"83.1"},"uses_additional_data":false,"paper_date":"2020-03-12","paper":"/paper/deep-domain-adversarial-image-generation-for","paper_url":"https://arxiv.org/abs/2003.06054v1","paper_title":"Deep Domain-Adversarial Image Generation for Domain Generalisation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":74,"model":"L2A-OT (Resnet-18)","metrics":{"Average Accuracy":"82.8"},"uses_additional_data":false,"paper_date":"2020-07-07","paper":"/paper/learning-to-generate-novel-domains-for-domain","paper_url":"https://arxiv.org/abs/2007.03304v3","paper_title":"Learning to Generate Novel Domains for Domain Generalization","code":"https://github.com/mousecpn/L2A-OT","n_code_links":1,"syntology":null},{"rank_in_archive_order":75,"model":"MASF (Resnet-50)","metrics":{"Average Accuracy":"82.67"},"uses_additional_data":false,"paper_date":"2019-10-29","paper":"/paper/domain-generalization-via-model-agnostic","paper_url":"https://arxiv.org/abs/1910.13580v1","paper_title":"Domain Generalization via Model-Agnostic Learning of Semantic Features","code":"https://github.com/biomedia-mira/masf","n_code_links":1,"syntology":null},{"rank_in_archive_order":76,"model":"CDANN (Resnet-50, DomainBed)","metrics":{"Average Accuracy":"82.6"},"uses_additional_data":false,"paper_date":"2018-09-01","paper":"/paper/deep-domain-generalization-via-conditional","paper_url":"http://openaccess.thecvf.com/content_ECCV_2018/html/Ya_Li_Deep_Domain_Generalization_ECCV_2018_paper.html","paper_title":"Deep Domain Generalization via Conditional Invariant Adversarial Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":77,"model":"DecAug (Resnet-18)","metrics":{"Average Accuracy":"82.4"},"uses_additional_data":false,"paper_date":"2020-10-02","paper":"/paper/decaug-augmenting-hoi-detection-via","paper_url":"https://arxiv.org/abs/2010.01007v1","paper_title":"DecAug: Augmenting HOI Detection via Decomposition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":78,"model":"DecAug (Resnet-18)","metrics":{"Average Accuracy":"82.39"},"uses_additional_data":false,"paper_date":"2020-12-17","paper":"/paper/decaug-out-of-distribution-generalization-via","paper_url":"https://arxiv.org/abs/2012.09382v1","paper_title":"DecAug: Out-of-Distribution Generalization via Decomposed Feature Representation and Semantic Augmentation","code":"https://github.com/HaoyueBaiZJU/DecAug","n_code_links":1,"syntology":null},{"rank_in_archive_order":79,"model":"SagNet (Resnet-50)","metrics":{"Average Accuracy":"82.3"},"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":80,"model":"EISNet (Resnet-18)","metrics":{"Average Accuracy":"82.15"},"uses_additional_data":false,"paper_date":"2020-07-18","paper":"/paper/learning-from-extrinsic-and-intrinsic","paper_url":"https://arxiv.org/abs/2007.09316v1","paper_title":"Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":81,"model":"MMLD (Resnet-18, k=2)","metrics":{"Average Accuracy":"81.83"},"uses_additional_data":false,"paper_date":"2019-11-18","paper":"/paper/domain-generalization-using-a-mixture-of","paper_url":"https://arxiv.org/abs/1911.07661v1","paper_title":"Domain Generalization Using a Mixture of Multiple Latent Domains","code":"https://github.com/mil-tokyo/dg_mmld","n_code_links":2,"syntology":null},{"rank_in_archive_order":82,"model":"FAR (Resnet-18)","metrics":{"Average Accuracy":"81.7"},"uses_additional_data":false,"paper_date":"2020-06-22","paper":"/paper/feature-alignment-and-restoration-for-domain","paper_url":"https://arxiv.org/abs/2006.12009v1","paper_title":"Feature Alignment and Restoration for Domain Generalization and Adaptation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":83,"model":"MetaReg (Resnet-18)","metrics":{"Average Accuracy":"81.7"},"uses_additional_data":false,"paper_date":"2018-12-01","paper":"/paper/metareg-towards-domain-generalization-using","paper_url":"http://papers.nips.cc/paper/7378-metareg-towards-domain-generalization-using-meta-regularization","paper_title":"MetaReg: Towards Domain Generalization using Meta-Regularization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":84,"model":"CuMix (Resnet-18)","metrics":{"Average Accuracy":"81.6"},"uses_additional_data":false,"paper_date":"2020-07-23","paper":"/paper/towards-recognizing-unseen-categories-in","paper_url":"https://arxiv.org/abs/2007.12256v2","paper_title":"Towards Recognizing Unseen Categories in Unseen Domains","code":"https://github.com/mancinimassimiliano/CuMix","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":85,"model":"Epi-FCR (Resnet-18)","metrics":{"Average Accuracy":"81.5"},"uses_additional_data":false,"paper_date":"2019-01-31","paper":"/paper/episodic-training-for-domain-generalization","paper_url":"https://arxiv.org/abs/1902.00113v3","paper_title":"Episodic Training for Domain Generalization","code":"https://github.com/HAHA-DL/Episodic-DG","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":4,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":86,"model":"S-MLDG (Resnet-18)","metrics":{"Average Accuracy":"81.5"},"uses_additional_data":false,"paper_date":"2020-04-03","paper":"/paper/sequential-learning-for-domain-generalization","paper_url":"https://arxiv.org/abs/2004.01377v1","paper_title":"Sequential Learning for Domain Generalization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":87,"model":"DMG (Resnet-18)","metrics":{"Average Accuracy":"81.46"},"uses_additional_data":false,"paper_date":"2020-08-28","paper":"/paper/learning-to-balance-specificity-and","paper_url":"https://arxiv.org/abs/2008.12839v1","paper_title":"Learning to Balance Specificity and Invariance for In and Out of Domain Generalization","code":"https://github.com/prithv1/DMG","n_code_links":1,"syntology":null},{"rank_in_archive_order":88,"model":"Jigsaw+Rotation (Resnet-18)","metrics":{"Average Accuracy":"81.41"},"uses_additional_data":false,"paper_date":"2020-07-24","paper":"/paper/self-supervised-learning-across-domains","paper_url":"https://arxiv.org/abs/2007.12368v2","paper_title":"Self-Supervised Learning Across Domains","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":89,"model":"ER (Resnet-18)","metrics":{"Average Accuracy":"81.38"},"uses_additional_data":false,"paper_date":"2020-12-01","paper":"/paper/domain-generalization-via-entropy","paper_url":"http://proceedings.neurips.cc/paper/2020/hash/b98249b38337c5088bbc660d8f872d6a-Abstract.html","paper_title":"Domain Generalization via Entropy Regularization","code":"https://github.com/sshan-zhao/DG_via_ER","n_code_links":1,"syntology":null},{"rank_in_archive_order":90,"model":"MASF (Resnet-18)","metrics":{"Average Accuracy":"81.04"},"uses_additional_data":false,"paper_date":"2019-10-29","paper":"/paper/domain-generalization-via-model-agnostic","paper_url":"https://arxiv.org/abs/1910.13580v1","paper_title":"Domain Generalization via Model-Agnostic Learning of Semantic Features","code":"https://github.com/biomedia-mira/masf","n_code_links":1,"syntology":null},{"rank_in_archive_order":91,"model":"D-SAM-Λ  (Resnet-18)","metrics":{"Average Accuracy":"80.72"},"uses_additional_data":false,"paper_date":"2018-09-28","paper":"/paper/domain-generalization-with-domain-specific","paper_url":"http://arxiv.org/abs/1809.10966v1","paper_title":"Domain Generalization with Domain-Specific Aggregation Modules","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":92,"model":"CrossGrad (Resnet-18)","metrics":{"Average Accuracy":"80.7"},"uses_additional_data":false,"paper_date":"2018-04-28","paper":"/paper/generalizing-across-domains-via-cross","paper_url":"http://arxiv.org/abs/1804.10745v2","paper_title":"Generalizing Across Domains via Cross-Gradient Training","code":"https://github.com/vihari/crossgrad","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":93,"model":"CSD (Resnet-18)","metrics":{"Average Accuracy":"80.69"},"uses_additional_data":false,"paper_date":"2020-03-28","paper":"/paper/efficient-domain-generalization-via-common","paper_url":"https://arxiv.org/abs/2003.12815v2","paper_title":"Efficient Domain Generalization via Common-Specific Low-Rank Decomposition","code":"https://github.com/vihari/csd","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":11,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":94,"model":"JiGen (Resnet-18)","metrics":{"Average Accuracy":"80.51"},"uses_additional_data":false,"paper_date":"2019-03-16","paper":"/paper/domain-generalization-by-solving-jigsaw","paper_url":"http://arxiv.org/abs/1903.06864v2","paper_title":"Domain Generalization by Solving Jigsaw Puzzles","code":"https://github.com/fmcarlucci/JigenDG","n_code_links":2,"syntology":null},{"rank_in_archive_order":95,"model":"DADG (Resnet-18)","metrics":{"Average Accuracy":"80.38"},"uses_additional_data":false,"paper_date":"2020-11-01","paper":"/paper/discriminative-adversarial-domain","paper_url":"https://arxiv.org/abs/2011.00444v2","paper_title":"Discriminative Adversarial Domain Generalization with Meta-learning based Cross-domain Validation","code":"https://github.com/Epi-NMT/DADG","n_code_links":3,"syntology":null},{"rank_in_archive_order":96,"model":"CCSA (Resnet-18)","metrics":{"Average Accuracy":"79.4"},"uses_additional_data":false,"paper_date":"2017-09-28","paper":"/paper/unified-deep-supervised-domain-adaptation-and","paper_url":"http://arxiv.org/abs/1709.10190v1","paper_title":"Unified Deep Supervised Domain Adaptation and Generalization","code":"https://github.com/adapt-python/adapt","n_code_links":3,"syntology":null},{"rank_in_archive_order":97,"model":"DDEC (Alexnet)","metrics":{"Average Accuracy":"79.15"},"uses_additional_data":false,"paper_date":"2019-09-18","paper":"/paper/towards-shape-biased-unsupervised","paper_url":"https://arxiv.org/abs/1909.08245v2","paper_title":"Towards Shape Biased Unsupervised Representation Learning for Domain Generalization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":98,"model":"Deep All (Resnet-18)","metrics":{"Average Accuracy":"79.05"},"uses_additional_data":false,"paper_date":"2019-03-16","paper":"/paper/domain-generalization-by-solving-jigsaw","paper_url":"http://arxiv.org/abs/1903.06864v2","paper_title":"Domain Generalization by Solving Jigsaw Puzzles","code":"https://github.com/fmcarlucci/JigenDG","n_code_links":2,"syntology":null},{"rank_in_archive_order":99,"model":"Stylized (Alexnet)","metrics":{"Average Accuracy":"77.31"},"uses_additional_data":false,"paper_date":"2021-01-22","paper":"/paper/rethinking-domain-generalization-baselines","paper_url":"https://arxiv.org/abs/2101.09060v2","paper_title":"Rethinking Domain Generalization Baselines","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":100,"model":"MMD-AAE (Resnet-18)","metrics":{"Average Accuracy":"77.0"},"uses_additional_data":false,"paper_date":"2018-06-01","paper":"/paper/domain-generalization-with-adversarial","paper_url":"http://openaccess.thecvf.com/content_cvpr_2018/html/Li_Domain_Generalization_With_CVPR_2018_paper.html","paper_title":"Domain Generalization With Adversarial Feature Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":101,"model":"DGIS (Alexnet, Painting)","metrics":{"Average Accuracy":"76.62"},"uses_additional_data":false,"paper_date":"2020-06-19","paper":"/paper/frustratingly-simple-domain-generalization","paper_url":"https://arxiv.org/abs/2006.11207v2","paper_title":"Frustratingly Simple Domain Generalization via Image Stylization","code":"https://github.com/GT-RIPL/DomainGeneralization-Stylization","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":102,"model":"RSC (AlexNet)","metrics":{"Average Accuracy":"76.05"},"uses_additional_data":false,"paper_date":"2020-07-05","paper":"/paper/self-challenging-improves-cross-domain","paper_url":"https://arxiv.org/abs/2007.02454v1","paper_title":"Self-Challenging Improves Cross-Domain Generalization","code":"https://github.com/facebookresearch/DomainBed","n_code_links":8,"syntology":{"n_ran":3,"n_unverified":4,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":103,"model":"ER (Alexnet)","metrics":{"Average Accuracy":"75.67"},"uses_additional_data":false,"paper_date":"2020-12-01","paper":"/paper/domain-generalization-via-entropy","paper_url":"http://proceedings.neurips.cc/paper/2020/hash/b98249b38337c5088bbc660d8f872d6a-Abstract.html","paper_title":"Domain Generalization via Entropy Regularization","code":"https://github.com/sshan-zhao/DG_via_ER","n_code_links":1,"syntology":null},{"rank_in_archive_order":104,"model":"SagNet (Alexnet)","metrics":{"Average Accuracy":"75.52"},"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":105,"model":"MASF (Alexnet)","metrics":{"Average Accuracy":"75.21"},"uses_additional_data":false,"paper_date":"2019-10-29","paper":"/paper/domain-generalization-via-model-agnostic","paper_url":"https://arxiv.org/abs/1910.13580v1","paper_title":"Domain Generalization via Model-Agnostic Learning of Semantic Features","code":"https://github.com/biomedia-mira/masf","n_code_links":1,"syntology":null},{"rank_in_archive_order":106,"model":"MMLD (Alexnet, k=3)","metrics":{"Average Accuracy":"74.38"},"uses_additional_data":false,"paper_date":"2019-11-18","paper":"/paper/domain-generalization-using-a-mixture-of","paper_url":"https://arxiv.org/abs/1911.07661v1","paper_title":"Domain Generalization Using a Mixture of Multiple Latent Domains","code":"https://github.com/mil-tokyo/dg_mmld","n_code_links":2,"syntology":null},{"rank_in_archive_order":107,"model":"Jigsaw+Rotation (Alexnet)","metrics":{"Average Accuracy":"74.08"},"uses_additional_data":false,"paper_date":"2020-07-24","paper":"/paper/self-supervised-learning-across-domains","paper_url":"https://arxiv.org/abs/2007.12368v2","paper_title":"Self-Supervised Learning Across Domains","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":108,"model":"G2DM (AlexNet)","metrics":{"Average Accuracy":"73.55"},"uses_additional_data":false,"paper_date":"2019-11-03","paper":"/paper/adversarial-target-invariant-representation","paper_url":"https://arxiv.org/abs/1911.00804v6","paper_title":"Generalizing to unseen domains via distribution matching","code":"https://github.com/belaalb/g2dm","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":109,"model":"GLOT-DR","metrics":{"Average Accuracy":"73.5"},"uses_additional_data":false,"paper_date":"2022-03-01","paper":"/paper/global-local-regularization-via","paper_url":"https://arxiv.org/abs/2203.00553v3","paper_title":"Global-Local Regularization Via Distributional Robustness","code":"https://github.com/viethoang1512/glot","n_code_links":1,"syntology":null},{"rank_in_archive_order":110,"model":"JiGen (Alexnet)","metrics":{"Average Accuracy":"73.38"},"uses_additional_data":false,"paper_date":"2019-03-16","paper":"/paper/domain-generalization-by-solving-jigsaw","paper_url":"http://arxiv.org/abs/1903.06864v2","paper_title":"Domain Generalization by Solving Jigsaw Puzzles","code":"https://github.com/fmcarlucci/JigenDG","n_code_links":2,"syntology":null},{"rank_in_archive_order":111,"model":"DMG (Alexnet)","metrics":{"Average Accuracy":"73.32"},"uses_additional_data":false,"paper_date":"2020-08-28","paper":"/paper/learning-to-balance-specificity-and","paper_url":"https://arxiv.org/abs/2008.12839v1","paper_title":"Learning to Balance Specificity and Invariance for In and Out of Domain Generalization","code":"https://github.com/prithv1/DMG","n_code_links":1,"syntology":null},{"rank_in_archive_order":112,"model":"MetaReg (Alexnet)","metrics":{"Average Accuracy":"72.62"},"uses_additional_data":false,"paper_date":"2018-12-01","paper":"/paper/metareg-towards-domain-generalization-using","paper_url":"http://papers.nips.cc/paper/7378-metareg-towards-domain-generalization-using-meta-regularization","paper_title":"MetaReg: Towards Domain Generalization using Meta-Regularization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":113,"model":"DADG (AlexNet)","metrics":{"Average Accuracy":"72.11"},"uses_additional_data":false,"paper_date":"2020-11-01","paper":"/paper/discriminative-adversarial-domain","paper_url":"https://arxiv.org/abs/2011.00444v2","paper_title":"Discriminative Adversarial Domain Generalization with Meta-learning based Cross-domain Validation","code":"https://github.com/Epi-NMT/DADG","n_code_links":3,"syntology":null},{"rank_in_archive_order":114,"model":"PAR (Alexnet)","metrics":{"Average Accuracy":"72.08"},"uses_additional_data":false,"paper_date":"2019-05-29","paper":"/paper/190513549","paper_url":"https://arxiv.org/abs/1905.13549v2","paper_title":"Learning Robust Global Representations by Penalizing Local Predictive Power","code":"https://github.com/HaohanWang/ImageNet-Sketch","n_code_links":4,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":115,"model":"Epi-FCR (Alexnet)","metrics":{"Average Accuracy":"72.00"},"uses_additional_data":false,"paper_date":"2019-01-31","paper":"/paper/episodic-training-for-domain-generalization","paper_url":"https://arxiv.org/abs/1902.00113v3","paper_title":"Episodic Training for Domain Generalization","code":"https://github.com/HAHA-DL/Episodic-DG","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":4,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":116,"model":"CAADG (Alexnet)","metrics":{"Average Accuracy":"71.98"},"uses_additional_data":false,"paper_date":"2019-11-29","paper":"/paper/correlation-aware-adversarial-domain","paper_url":"https://arxiv.org/abs/1911.12983v1","paper_title":"Correlation-aware Adversarial Domain Adaptation and Generalization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":117,"model":"Deep All (Alexnet)","metrics":{"Average Accuracy":"71.52"},"uses_additional_data":false,"paper_date":"2019-03-16","paper":"/paper/domain-generalization-by-solving-jigsaw","paper_url":"http://arxiv.org/abs/1903.06864v2","paper_title":"Domain Generalization by Solving Jigsaw Puzzles","code":"https://github.com/fmcarlucci/JigenDG","n_code_links":2,"syntology":null},{"rank_in_archive_order":118,"model":"D-SAM (Alexnet)","metrics":{"Average Accuracy":"71.20"},"uses_additional_data":false,"paper_date":"2018-09-28","paper":"/paper/domain-generalization-with-domain-specific","paper_url":"http://arxiv.org/abs/1809.10966v1","paper_title":"Domain Generalization with Domain-Specific Aggregation Modules","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":119,"model":"VREx (Alexnet)","metrics":{"Average Accuracy":"71.14"},"uses_additional_data":false,"paper_date":"2020-03-02","paper":"/paper/out-of-distribution-generalization-via-risk","paper_url":"https://arxiv.org/abs/2003.00688v5","paper_title":"Out-of-Distribution Generalization via Risk Extrapolation (REx)","code":"https://github.com/thuml/Transfer-Learning-Library","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":120,"model":"RC (Alexnet)","metrics":{"Average Accuracy":"70.53"},"uses_additional_data":false,"paper_date":"2020-07-25","paper":"/paper/robust-and-generalizable-visual","paper_url":"https://arxiv.org/abs/2007.13003v3","paper_title":"Robust and Generalizable Visual Representation Learning via Random Convolutions","code":"https://github.com/wildphoton/RandConv","n_code_links":5,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":121,"model":"FeatureCritic (Alexnet)","metrics":{"Average Accuracy":"70.40"},"uses_additional_data":false,"paper_date":"2019-01-31","paper":"/paper/feature-critic-networks-for-heterogeneous","paper_url":"https://arxiv.org/abs/1901.11448v3","paper_title":"Feature-Critic Networks for Heterogeneous Domain Generalization","code":"https://github.com/liyiying/Feature_Critic","n_code_links":2,"syntology":null},{"rank_in_archive_order":122,"model":"BestSources (Alexnet)","metrics":{"Average Accuracy":"70.30"},"uses_additional_data":false,"paper_date":"2018-06-15","paper":"/paper/best-sources-forward-domain-generalization","paper_url":"http://arxiv.org/abs/1806.05810v1","paper_title":"Best sources forward: domain generalization through source-specific nets","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":123,"model":"Hex (Alexnet)","metrics":{"Average Accuracy":"70.20"},"uses_additional_data":false,"paper_date":"2019-03-02","paper":"/paper/learning-robust-representations-by-projecting-1","paper_url":"http://arxiv.org/abs/1903.06256v1","paper_title":"Learning Robust Representations by Projecting Superficial Statistics Out","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":124,"model":"MLDG (Alexnet)","metrics":{"Average Accuracy":"70.01"},"uses_additional_data":false,"paper_date":"2017-10-10","paper":"/paper/learning-to-generalize-meta-learning-for","paper_url":"http://arxiv.org/abs/1710.03463v1","paper_title":"Learning to Generalize: Meta-Learning for Domain Generalization","code":"https://github.com/thuml/Transfer-Learning-Library","n_code_links":5,"syntology":{"n_ran":2,"n_unverified":9,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":125,"model":"JAN-COMBO (Alexnet)","metrics":{"Average Accuracy":"69.45"},"uses_additional_data":false,"paper_date":"2018-12-21","paper":"/paper/multi-component-image-translation-for-deep","paper_url":"http://arxiv.org/abs/1812.08974v1","paper_title":"Multi-component Image Translation for Deep Domain Generalization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":126,"model":"Rotation+Gabor+DeepCluster (Alexnet)","metrics":{"Average Accuracy":"69.32"},"uses_additional_data":false,"paper_date":"2020-03-30","paper":"/paper/improving-out-of-distribution-generalization","paper_url":"https://arxiv.org/abs/2003.13525v1","paper_title":"Improving out-of-distribution generalization via multi-task self-supervised pretraining","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":127,"model":"TF (Alexnet)","metrics":{"Average Accuracy":"69.21"},"uses_additional_data":false,"paper_date":"2017-10-09","paper":"/paper/deeper-broader-and-artier-domain","paper_url":"http://arxiv.org/abs/1710.03077v1","paper_title":"Deeper, Broader and Artier Domain Generalization","code":"https://github.com/facebookresearch/DomainBed","n_code_links":6,"syntology":{"n_ran":3,"n_unverified":4,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":128,"model":"CIDDG (Alexnet)","metrics":{"Average Accuracy":"68.88"},"uses_additional_data":false,"paper_date":"2018-09-01","paper":"/paper/deep-domain-generalization-via-conditional","paper_url":"http://openaccess.thecvf.com/content_ECCV_2018/html/Ya_Li_Deep_Domain_Generalization_ECCV_2018_paper.html","paper_title":"Deep Domain Generalization via Conditional Invariant Adversarial Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":129,"model":"DSN (Alexnet)","metrics":{"Average Accuracy":"67.37"},"uses_additional_data":false,"paper_date":"2016-08-22","paper":"/paper/domain-separation-networks","paper_url":"http://arxiv.org/abs/1608.06019v1","paper_title":"Domain Separation Networks","code":"https://github.com/tensorflow/models","n_code_links":6,"syntology":{"n_ran":5,"n_unverified":9,"n_samples":14,"n_pointer_only_licence":6}},{"rank_in_archive_order":130,"model":"LRE-SVM","metrics":{"Average Accuracy":"58.99"},"uses_additional_data":false,"paper_date":"2017-10-09","paper":"/paper/deeper-broader-and-artier-domain","paper_url":"http://arxiv.org/abs/1710.03077v1","paper_title":"Deeper, Broader and Artier Domain Generalization","code":"https://github.com/facebookresearch/DomainBed","n_code_links":6,"syntology":{"n_ran":3,"n_unverified":4,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":131,"model":"SVM","metrics":{"Average Accuracy":"58.74"},"uses_additional_data":false,"paper_date":"2017-10-09","paper":"/paper/deeper-broader-and-artier-domain","paper_url":"http://arxiv.org/abs/1710.03077v1","paper_title":"Deeper, Broader and Artier Domain Generalization","code":"https://github.com/facebookresearch/DomainBed","n_code_links":6,"syntology":{"n_ran":3,"n_unverified":4,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":132,"model":"SGE (GNN-Tag)","metrics":{"Average Accuracy":"47.45"},"uses_additional_data":false,"paper_date":"2021-09-13","paper":"/paper/shape-biased-domain-generalization-via-shock","paper_url":"https://arxiv.org/abs/2109.05671v1","paper_title":"Shape-Biased Domain Generalization via Shock Graph Embeddings","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":133,"model":"BayesPrompt","metrics":{"Average Accuracy":"0"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"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":53,"rows_with_any_sample_ran":44,"distinct_papers_with_graph_line":36,"distinct_papers_with_any_sample_ran":30,"samples_over_distinct_papers":{"n_ran":127,"n_unverified":114,"n_samples":241,"n_pointer_only_licence":65,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":178,"n_unverified":156,"n_samples":334,"n_pointer_only_licence":72,"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"}}}