{"url":"/sota/domain-generalization-on-imagenet-r","task":{"name":"Domain Generalization","url":"/task/domain-generalization","note":null},"dataset":{"name":"ImageNet-R","url":"/dataset/imagenet-r"},"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":["Top-1 Error Rate"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Top-1 Error Rate":null}},"counts":{"rows":39,"rows_with_code":38,"rows_with_paper_page":39,"rows_dated":39,"rows_using_additional_data":13},"rows":[{"rank_in_archive_order":1,"model":"Model soups (BASIC-L)","metrics":{"Top-1 Error Rate":"3.90"},"uses_additional_data":true,"paper_date":"2022-03-10","paper":"/paper/model-soups-averaging-weights-of-multiple","paper_url":"https://arxiv.org/abs/2203.05482v3","paper_title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","code":"https://github.com/mlfoundations/model-soups","n_code_links":6,"syntology":{"n_ran":8,"n_unverified":9,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"Model soups (ViT-G/14)","metrics":{"Top-1 Error Rate":"4.54"},"uses_additional_data":true,"paper_date":"2022-03-10","paper":"/paper/model-soups-averaging-weights-of-multiple","paper_url":"https://arxiv.org/abs/2203.05482v3","paper_title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","code":"https://github.com/mlfoundations/model-soups","n_code_links":6,"syntology":{"n_ran":8,"n_unverified":9,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"CAR-FT (CLIP, ViT-L/14@336px)","metrics":{"Top-1 Error Rate":"10.3"},"uses_additional_data":true,"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":4,"model":"FAN-Hybrid-L(IN-21K, 384))","metrics":{"Top-1 Error Rate":"28.9"},"uses_additional_data":true,"paper_date":"2022-04-26","paper":"/paper/understanding-the-robustness-in-vision","paper_url":"https://arxiv.org/abs/2204.12451v4","paper_title":"Understanding The Robustness in Vision Transformers","code":"https://github.com/nvlabs/fan","n_code_links":2,"syntology":null},{"rank_in_archive_order":5,"model":"CAFormer-B36 (IN21K, 384)","metrics":{"Top-1 Error Rate":"29.6"},"uses_additional_data":true,"paper_date":"2022-10-24","paper":"/paper/metaformer-baselines-for-vision","paper_url":"https://arxiv.org/abs/2210.13452v4","paper_title":"MetaFormer Baselines for Vision","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":8,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"LLE (ViT-B/16, SWAG, Edge Aug)","metrics":{"Top-1 Error Rate":"31.3"},"uses_additional_data":true,"paper_date":"2022-12-09","paper":"/paper/a-whac-a-mole-dilemma-shortcuts-come-in","paper_url":"https://arxiv.org/abs/2212.04825v2","paper_title":"A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others","code":"https://github.com/facebookresearch/Whac-A-Mole","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"CAFormer-B36 (IN21K)","metrics":{"Top-1 Error Rate":"31.7"},"uses_additional_data":true,"paper_date":"2022-10-24","paper":"/paper/metaformer-baselines-for-vision","paper_url":"https://arxiv.org/abs/2210.13452v4","paper_title":"MetaFormer Baselines for Vision","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":8,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"ConvNeXt-XL (Im21k, 384)","metrics":{"Top-1 Error Rate":"31.8"},"uses_additional_data":true,"paper_date":"2022-01-10","paper":"/paper/a-convnet-for-the-2020s","paper_url":"https://arxiv.org/abs/2201.03545v2","paper_title":"A ConvNet for the 2020s","code":"https://github.com/keras-team/keras/blob/master/keras/applications/convnext.py","n_code_links":54,"syntology":{"n_ran":57,"n_unverified":23,"n_samples":80,"n_pointer_only_licence":11}},{"rank_in_archive_order":9,"model":"LLE (ViT-H/14, MAE, Edge Aug)","metrics":{"Top-1 Error Rate":"33.1"},"uses_additional_data":false,"paper_date":"2022-12-09","paper":"/paper/a-whac-a-mole-dilemma-shortcuts-come-in","paper_url":"https://arxiv.org/abs/2212.04825v2","paper_title":"A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others","code":"https://github.com/facebookresearch/Whac-A-Mole","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"MAE (ViT-H, 448)","metrics":{"Top-1 Error Rate":"33.5"},"uses_additional_data":false,"paper_date":"2021-11-11","paper":"/paper/masked-autoencoders-are-scalable-vision","paper_url":"https://arxiv.org/abs/2111.06377v2","paper_title":"Masked Autoencoders Are Scalable Vision Learners","code":"https://github.com/facebookresearch/mae","n_code_links":58,"syntology":{"n_ran":86,"n_unverified":51,"n_samples":137,"n_pointer_only_licence":73}},{"rank_in_archive_order":11,"model":"ConvFormer-B36 (IN21K, 384)","metrics":{"Top-1 Error Rate":"33.5"},"uses_additional_data":true,"paper_date":"2022-10-24","paper":"/paper/metaformer-baselines-for-vision","paper_url":"https://arxiv.org/abs/2210.13452v4","paper_title":"MetaFormer Baselines for Vision","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":8,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"MAE+DAT (ViT-H)","metrics":{"Top-1 Error Rate":"34.39"},"uses_additional_data":false,"paper_date":"2022-09-16","paper":"/paper/enhance-the-visual-representation-via","paper_url":"https://arxiv.org/abs/2209.07735v1","paper_title":"Enhance the Visual Representation via Discrete Adversarial Training","code":"https://github.com/alibaba/easyrobust/tree/main/examples/imageclassification/imagenet/dat","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":1,"n_samples":11,"n_pointer_only_licence":1}},{"rank_in_archive_order":13,"model":"ConvFormer-B36 (IN21K)","metrics":{"Top-1 Error Rate":"34.7"},"uses_additional_data":true,"paper_date":"2022-10-24","paper":"/paper/metaformer-baselines-for-vision","paper_url":"https://arxiv.org/abs/2210.13452v4","paper_title":"MetaFormer Baselines for Vision","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":8,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"Discrete Adversarial Distillation (ViT-B,224)","metrics":{"Top-1 Error Rate":"34.9"},"uses_additional_data":false,"paper_date":"2023-11-02","paper":"/paper/distilling-out-of-distribution-robustness-1","paper_url":"https://arxiv.org/abs/2311.01441v2","paper_title":"Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models","code":"https://github.com/lapisrocks/DiscreteAdversarialDistillation","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"GPaCo (ViT-L)","metrics":{"Top-1 Error Rate":"39.7"},"uses_additional_data":false,"paper_date":"2022-09-26","paper":"/paper/generalized-parametric-contrastive-learning","paper_url":"https://arxiv.org/abs/2209.12400v2","paper_title":"Generalized Parametric Contrastive Learning","code":"https://github.com/dvlab-research/parametric-contrastive-learning","n_code_links":4,"syntology":null},{"rank_in_archive_order":16,"model":"VOLO-D5+HAT","metrics":{"Top-1 Error Rate":"40.3"},"uses_additional_data":false,"paper_date":"2022-04-03","paper":"/paper/improving-vision-transformers-by-revisiting","paper_url":"https://arxiv.org/abs/2204.00993v3","paper_title":"Improving Vision Transformers by Revisiting High-frequency Components","code":"https://github.com/jiawangbai/HAT","n_code_links":1,"syntology":{"n_ran":11,"n_unverified":3,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"Pyramid Adversarial Training Improves ViT (Im21k)","metrics":{"Top-1 Error Rate":"42.16"},"uses_additional_data":true,"paper_date":"2021-11-30","paper":"/paper/pyramid-adversarial-training-improves-vit","paper_url":"https://arxiv.org/abs/2111.15121v2","paper_title":"Pyramid Adversarial Training Improves ViT Performance","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"FAN-L-Hybrid+STL","metrics":{"Top-1 Error Rate":"43.4"},"uses_additional_data":false,"paper_date":"2024-01-08","paper":"/paper/fully-attentional-networks-with-self-emerging-1","paper_url":"https://arxiv.org/abs/2401.03844v1","paper_title":"Fully Attentional Networks with Self-emerging Token Labeling","code":"https://github.com/NVlabs/STL","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"SEER (RegNet10B)","metrics":{"Top-1 Error Rate":"43.9"},"uses_additional_data":true,"paper_date":"2022-02-16","paper":"/paper/vision-models-are-more-robust-and-fair-when","paper_url":"https://arxiv.org/abs/2202.08360v2","paper_title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","code":"https://github.com/facebookresearch/vissl","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"DiscreteViT","metrics":{"Top-1 Error Rate":"44.74"},"uses_additional_data":false,"paper_date":"2021-11-20","paper":"/paper/discrete-representations-strengthen-vision-1","paper_url":"https://arxiv.org/abs/2111.10493v2","paper_title":"Discrete Representations Strengthen Vision Transformer Robustness","code":"https://github.com/alibaba/easyrobust/tree/main/examples/imageclassification/imagenet/drvit","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"CAFormer-B36 (384)","metrics":{"Top-1 Error Rate":"45"},"uses_additional_data":false,"paper_date":"2022-10-24","paper":"/paper/metaformer-baselines-for-vision","paper_url":"https://arxiv.org/abs/2210.13452v4","paper_title":"MetaFormer Baselines for Vision","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":8,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"Pyramid Adversarial Training Improves ViT","metrics":{"Top-1 Error Rate":"46.08"},"uses_additional_data":false,"paper_date":"2021-11-30","paper":"/paper/pyramid-adversarial-training-improves-vit","paper_url":"https://arxiv.org/abs/2111.15121v2","paper_title":"Pyramid Adversarial Training Improves ViT Performance","code":"https://github.com/google-research/scenic/tree/main/scenic/projects/adversarialtraining","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"CAFormer-B36","metrics":{"Top-1 Error Rate":"46.1"},"uses_additional_data":false,"paper_date":"2022-10-24","paper":"/paper/metaformer-baselines-for-vision","paper_url":"https://arxiv.org/abs/2210.13452v4","paper_title":"MetaFormer Baselines for Vision","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":8,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":24,"model":"ConvFormer-B36 (384)","metrics":{"Top-1 Error Rate":"47.8"},"uses_additional_data":false,"paper_date":"2022-10-24","paper":"/paper/metaformer-baselines-for-vision","paper_url":"https://arxiv.org/abs/2210.13452v4","paper_title":"MetaFormer Baselines for Vision","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":8,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":25,"model":"ConvFormer-B36","metrics":{"Top-1 Error Rate":"48.9"},"uses_additional_data":false,"paper_date":"2022-10-24","paper":"/paper/metaformer-baselines-for-vision","paper_url":"https://arxiv.org/abs/2210.13452v4","paper_title":"MetaFormer Baselines for Vision","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":8,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":26,"model":"RVT-B*","metrics":{"Top-1 Error Rate":"51.3"},"uses_additional_data":false,"paper_date":"2021-05-17","paper":"/paper/rethinking-the-design-principles-of-robust","paper_url":"https://arxiv.org/abs/2105.07926v4","paper_title":"Towards Robust Vision Transformer","code":"https://github.com/alibaba/easyrobust","n_code_links":2,"syntology":null},{"rank_in_archive_order":27,"model":"Sequencer2D-L","metrics":{"Top-1 Error Rate":"51.9"},"uses_additional_data":false,"paper_date":"2022-05-04","paper":"/paper/sequencer-deep-lstm-for-image-classification","paper_url":"https://arxiv.org/abs/2205.01972v4","paper_title":"Sequencer: Deep LSTM for Image Classification","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":5,"syntology":{"n_ran":4,"n_unverified":5,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":28,"model":"RVT-S*","metrics":{"Top-1 Error Rate":"52.3"},"uses_additional_data":false,"paper_date":"2021-05-17","paper":"/paper/rethinking-the-design-principles-of-robust","paper_url":"https://arxiv.org/abs/2105.07926v4","paper_title":"Towards Robust Vision Transformer","code":"https://github.com/alibaba/easyrobust","n_code_links":2,"syntology":null},{"rank_in_archive_order":29,"model":"DeepAugment+AugMix (ResNet-50)","metrics":{"Top-1 Error Rate":" 53.2 "},"uses_additional_data":false,"paper_date":"2020-06-29","paper":"/paper/the-many-faces-of-robustness-a-critical","paper_url":"https://arxiv.org/abs/2006.16241v3","paper_title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","code":"https://github.com/hendrycks/imagenet-r","n_code_links":1,"syntology":{"n_ran":14,"n_unverified":0,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":30,"model":"PRIME with JSD (ResNet-50)","metrics":{"Top-1 Error Rate":"53.7"},"uses_additional_data":false,"paper_date":"2021-12-27","paper":"/paper/prime-a-few-primitives-can-boost-robustness","paper_url":"https://arxiv.org/abs/2112.13547v2","paper_title":"PRIME: A few primitives can boost robustness to common corruptions","code":"https://github.com/amodas/PRIME-augmentations","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":31,"model":"RVT-Ti*","metrics":{"Top-1 Error Rate":"56.1"},"uses_additional_data":false,"paper_date":"2021-05-17","paper":"/paper/rethinking-the-design-principles-of-robust","paper_url":"https://arxiv.org/abs/2105.07926v4","paper_title":"Towards Robust Vision Transformer","code":"https://github.com/alibaba/easyrobust","n_code_links":2,"syntology":null},{"rank_in_archive_order":32,"model":"PRIME (ResNet-50)","metrics":{"Top-1 Error Rate":"57.1"},"uses_additional_data":false,"paper_date":"2021-12-27","paper":"/paper/prime-a-few-primitives-can-boost-robustness","paper_url":"https://arxiv.org/abs/2112.13547v2","paper_title":"PRIME: A few primitives can boost robustness to common corruptions","code":"https://github.com/amodas/PRIME-augmentations","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"DeepAugment (ResNet-50)","metrics":{"Top-1 Error Rate":"57.8"},"uses_additional_data":false,"paper_date":"2020-06-29","paper":"/paper/the-many-faces-of-robustness-a-critical","paper_url":"https://arxiv.org/abs/2006.16241v3","paper_title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","code":"https://github.com/hendrycks/imagenet-r","n_code_links":1,"syntology":{"n_ran":14,"n_unverified":0,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":34,"model":"Stylized ImageNet (ResNet-50)","metrics":{"Top-1 Error Rate":"58.5 "},"uses_additional_data":true,"paper_date":"2018-11-29","paper":"/paper/imagenet-trained-cnns-are-biased-towards","paper_url":"https://arxiv.org/abs/1811.12231v3","paper_title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","code":"https://github.com/rgeirhos/texture-vs-shape","n_code_links":7,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":35,"model":"AugMix (ResNet-50)","metrics":{"Top-1 Error Rate":"58.9"},"uses_additional_data":false,"paper_date":"2019-12-05","paper":"/paper/augmix-a-simple-data-processing-method-to","paper_url":"https://arxiv.org/abs/1912.02781v2","paper_title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":15,"syntology":{"n_ran":46,"n_unverified":5,"n_samples":51,"n_pointer_only_licence":25}},{"rank_in_archive_order":36,"model":"ResNet-50","metrics":{"Top-1 Error Rate":"63.9"},"uses_additional_data":false,"paper_date":"2015-12-10","paper":"/paper/deep-residual-learning-for-image-recognition","paper_url":"http://arxiv.org/abs/1512.03385v1","paper_title":"Deep Residual Learning for Image Recognition","code":"https://github.com/tensorflow/models/tree/master/research/deeplab","n_code_links":484,"syntology":{"n_ran":242,"n_unverified":135,"n_samples":377,"n_pointer_only_licence":187}},{"rank_in_archive_order":37,"model":"ResNet-152x2-SAM","metrics":{"Top-1 Error Rate":"71.9"},"uses_additional_data":false,"paper_date":"2021-06-03","paper":"/paper/when-vision-transformers-outperform-resnets","paper_url":"https://arxiv.org/abs/2106.01548v3","paper_title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","code":"https://github.com/google-research/vision_transformer","n_code_links":2,"syntology":null},{"rank_in_archive_order":38,"model":"ViT-B/16-SAM","metrics":{"Top-1 Error Rate":"73.6"},"uses_additional_data":false,"paper_date":"2021-06-03","paper":"/paper/when-vision-transformers-outperform-resnets","paper_url":"https://arxiv.org/abs/2106.01548v3","paper_title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","code":"https://github.com/google-research/vision_transformer","n_code_links":2,"syntology":null},{"rank_in_archive_order":39,"model":"Mixer-B/8-SAM","metrics":{"Top-1 Error Rate":"76.5"},"uses_additional_data":false,"paper_date":"2021-06-03","paper":"/paper/when-vision-transformers-outperform-resnets","paper_url":"https://arxiv.org/abs/2106.01548v3","paper_title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","code":"https://github.com/google-research/vision_transformer","n_code_links":2,"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":23,"rows_with_any_sample_ran":22,"distinct_papers_with_graph_line":13,"distinct_papers_with_any_sample_ran":12,"samples_over_distinct_papers":{"n_ran":487,"n_unverified":242,"n_samples":729,"n_pointer_only_licence":297,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":523,"n_unverified":273,"n_samples":796,"n_pointer_only_licence":297,"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"}}}