{"url":"/sota/domain-generalization-on-imagenet-c","task":{"name":"Domain Generalization","url":"/task/domain-generalization","note":null},"dataset":{"name":"ImageNet-C","url":"/dataset/imagenet-c"},"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":["mean Corruption Error (mCE)","Top 1 Accuracy","Number of params"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"mean Corruption Error (mCE)":"lower","Top 1 Accuracy":"higher","Number of params":"lower"}},"counts":{"rows":47,"rows_with_code":47,"rows_with_paper_page":47,"rows_dated":47,"rows_using_additional_data":16},"rows":[{"rank_in_archive_order":1,"model":"DINOv2 (ViT-g/14, frozen model, linear eval)","metrics":{"Number of params":"1100M","mean Corruption Error (mCE)":"28.2"},"uses_additional_data":true,"paper_date":"2023-04-14","paper":"/paper/dinov2-learning-robust-visual-features","paper_url":"https://arxiv.org/abs/2304.07193v2","paper_title":"DINOv2: Learning Robust Visual Features without Supervision","code":"https://github.com/huggingface/transformers","n_code_links":26,"syntology":{"n_ran":21,"n_unverified":25,"n_samples":46,"n_pointer_only_licence":12}},{"rank_in_archive_order":2,"model":"CAFormer-B36 (IN21K, 384)","metrics":{"Number of params":"99M","mean Corruption Error (mCE)":"30.8"},"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":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"MAE+DAT (ViT-H)","metrics":{"Number of params":"632M","mean Corruption Error (mCE)":"31.4"},"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":4,"model":"DINOv2 (ViT-L/14, frozen model, linear eval)","metrics":{"Number of params":"307M","mean Corruption Error (mCE)":"31.5"},"uses_additional_data":true,"paper_date":"2023-04-14","paper":"/paper/dinov2-learning-robust-visual-features","paper_url":"https://arxiv.org/abs/2304.07193v2","paper_title":"DINOv2: Learning Robust Visual Features without Supervision","code":"https://github.com/huggingface/transformers","n_code_links":26,"syntology":{"n_ran":21,"n_unverified":25,"n_samples":46,"n_pointer_only_licence":12}},{"rank_in_archive_order":5,"model":"CAFormer-B36 (IN21K)","metrics":{"mean Corruption Error (mCE)":"31.8"},"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":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"MAE (ViT-H)","metrics":{"Number of params":"632M","mean Corruption Error (mCE)":"33.8"},"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":71,"n_unverified":66,"n_samples":137,"n_pointer_only_licence":73}},{"rank_in_archive_order":7,"model":"ConvFormer-B36 (IN21K)","metrics":{"mean Corruption Error (mCE)":"35.0"},"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":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"FAN-L-Hybrid (IN-22k)","metrics":{"Number of params":"77M","Top 1 Accuracy":"73.6","mean Corruption Error (mCE)":"35.8"},"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":9,"model":"Pyramid Adversarial Training Improves ViT (Im21k)","metrics":{"Number of params":"87M","mean Corruption Error (mCE)":"36.80"},"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":10,"model":"VOLO-D5+HAT","metrics":{"Number of params":"296M","mean Corruption Error (mCE)":"38.4"},"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":10,"n_unverified":4,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"DiscreteViT (Im21k)","metrics":{"Number of params":"87M","mean Corruption Error (mCE)":"38.74"},"uses_additional_data":true,"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":12,"model":"ConvNeXt-XL (Im21k) (augmentation overlap with ImageNet-C)","metrics":{"Number of params":"350M","mean Corruption Error (mCE)":"38.8"},"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":54,"n_unverified":26,"n_samples":80,"n_pointer_only_licence":11}},{"rank_in_archive_order":13,"model":"GPaCo (ViT-L)","metrics":{"mean Corruption Error (mCE)":"39.0"},"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":14,"model":"FAN-B-Hybrid (IN-22k)","metrics":{"Number of params":"50M","Top 1 Accuracy":"70.5","mean Corruption Error (mCE)":"41.0"},"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":15,"model":"Pyramid Adversarial Training Improves ViT","metrics":{"mean Corruption Error (mCE)":"41.42"},"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":16,"model":"FAN-L-Hybrid+STL","metrics":{"Number of params":"77M","Top 1 Accuracy":"69.2","mean Corruption Error (mCE)":"42.1"},"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":17,"model":"QualNet (ResNeXt101)","metrics":{"mean Corruption Error (mCE)":"42.5"},"uses_additional_data":false,"paper_date":"2021-06-19","paper":"/paper/quality-agnostic-image-recognition-via","paper_url":"http://openaccess.thecvf.com//content/CVPR2021/html/Kim_Quality-Agnostic_Image_Recognition_via_Invertible_Decoder_CVPR_2021_paper.html","paper_title":"Quality-Agnostic Image Recognition via Invertible Decoder","code":"https://github.com/tjdhg456/QualNet-Pytorch","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"CAFormer-B36","metrics":{"mean Corruption Error (mCE)":"42.6"},"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":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"DINOv2 (ViT-B/14, frozen model, linear eval)","metrics":{"Number of params":"85M","mean Corruption Error (mCE)":"42.7"},"uses_additional_data":true,"paper_date":"2023-04-14","paper":"/paper/dinov2-learning-robust-visual-features","paper_url":"https://arxiv.org/abs/2304.07193v2","paper_title":"DINOv2: Learning Robust Visual Features without Supervision","code":"https://github.com/huggingface/transformers","n_code_links":26,"syntology":{"n_ran":21,"n_unverified":25,"n_samples":46,"n_pointer_only_licence":12}},{"rank_in_archive_order":20,"model":"FAN-L-Hybrid","metrics":{"Number of params":"77M","Top 1 Accuracy":"67.7","mean Corruption Error (mCE)":"43.0"},"uses_additional_data":false,"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":21,"model":"DrViT","metrics":{"mean Corruption Error (mCE)":"46.22"},"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":22,"model":"DiscreteViT","metrics":{"Number of params":"87M","mean Corruption Error (mCE)":"46.22"},"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":23,"model":"ConvFormer-B36","metrics":{"mean Corruption Error (mCE)":"46.3"},"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":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":24,"model":"RVT-B*","metrics":{"mean Corruption Error (mCE)":"46.8"},"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":25,"model":"Sequencer2D-L","metrics":{"mean Corruption Error (mCE)":"48.9"},"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":26,"model":"RVT-S*","metrics":{"mean Corruption Error (mCE)":"49.4"},"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":"ResNet-50 (PushPull-Conv) + PRIME","metrics":{"Number of params":"25.6","Top 1 Accuracy":"69.4","mean Corruption Error (mCE)":"49.95"},"uses_additional_data":false,"paper_date":"2024-08-07","paper":"/paper/pushpull-net-inhibition-driven-resnet-robust","paper_url":"https://arxiv.org/abs/2408.04077v2","paper_title":"PushPull-Net: Inhibition-driven ResNet robust to image corruptions","code":"https://github.com/bgswaroop/pushpull-conv","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"QualNet (ResNet-50)","metrics":{"mean Corruption Error (mCE)":"50.6"},"uses_additional_data":false,"paper_date":"2021-06-19","paper":"/paper/quality-agnostic-image-recognition-via","paper_url":"http://openaccess.thecvf.com//content/CVPR2021/html/Kim_Quality-Agnostic_Image_Recognition_via_Invertible_Decoder_CVPR_2021_paper.html","paper_title":"Quality-Agnostic Image Recognition via Invertible Decoder","code":"https://github.com/tjdhg456/QualNet-Pytorch","n_code_links":1,"syntology":null},{"rank_in_archive_order":29,"model":"PRIME + DeepAugment (ResNet-50)","metrics":{"Top 1 Accuracy":"59.9","mean Corruption Error (mCE)":"51.3"},"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":5,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":30,"model":"GFNet-S","metrics":{"mean Corruption Error (mCE)":"53.8"},"uses_additional_data":false,"paper_date":"2021-07-01","paper":"/paper/global-filter-networks-for-image","paper_url":"https://arxiv.org/abs/2107.00645v2","paper_title":"Global Filter Networks for Image Classification","code":"https://github.com/raoyongming/GFNet","n_code_links":4,"syntology":{"n_ran":6,"n_unverified":4,"n_samples":10,"n_pointer_only_licence":5}},{"rank_in_archive_order":31,"model":"DINOv2 (ViT-S/14, frozen model, linear eval)","metrics":{"Number of params":"21M","mean Corruption Error (mCE)":"54.4"},"uses_additional_data":true,"paper_date":"2023-04-14","paper":"/paper/dinov2-learning-robust-visual-features","paper_url":"https://arxiv.org/abs/2304.07193v2","paper_title":"DINOv2: Learning Robust Visual Features without Supervision","code":"https://github.com/huggingface/transformers","n_code_links":26,"syntology":{"n_ran":21,"n_unverified":25,"n_samples":46,"n_pointer_only_licence":12}},{"rank_in_archive_order":32,"model":"PRIME with JSD (ResNet-50)","metrics":{"Top 1 Accuracy":"56.4","mean Corruption Error (mCE)":"55.5"},"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":5,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"RVT-Ti*","metrics":{"mean Corruption Error (mCE)":"57.0"},"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":34,"model":"PRIME (ResNet-50)","metrics":{"Top 1 Accuracy":"55.0","mean Corruption Error (mCE)":"57.5"},"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":5,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":35,"model":"APR-SP + DeepAugment (ResNet-50)","metrics":{"mean Corruption Error (mCE)":"57.5"},"uses_additional_data":false,"paper_date":"2021-08-19","paper":"/paper/amplitude-phase-recombination-rethinking","paper_url":"https://arxiv.org/abs/2108.08487v1","paper_title":"Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain","code":"https://github.com/iCGY96/APR","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":36,"model":"DeepAugment (ResNet-50)","metrics":{"mean Corruption Error (mCE)":" 60.4"},"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":13,"n_unverified":1,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":37,"model":"APR-SP (ResNet-50)","metrics":{"mean Corruption Error (mCE)":"65.0"},"uses_additional_data":false,"paper_date":"2021-08-19","paper":"/paper/amplitude-phase-recombination-rethinking","paper_url":"https://arxiv.org/abs/2108.08487v1","paper_title":"Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain","code":"https://github.com/iCGY96/APR","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":38,"model":"AugMix (ResNet-50)","metrics":{"mean Corruption Error (mCE)":"65.3"},"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":43,"n_unverified":8,"n_samples":51,"n_pointer_only_licence":25}},{"rank_in_archive_order":39,"model":"Stylized ImageNet (ResNet-50)","metrics":{"mean Corruption Error (mCE)":"69.3"},"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":40,"model":"Group-wise Inhibition (ResNet-50)","metrics":{"mean Corruption Error (mCE)":"69.6"},"uses_additional_data":false,"paper_date":"2021-03-03","paper":"/paper/group-wise-inhibition-based-feature","paper_url":"https://arxiv.org/abs/2103.02152v3","paper_title":"Group-wise Inhibition based Feature Regularization for Robust Classification","code":"https://github.com/LinusWu/TENET_Training","n_code_links":1,"syntology":null},{"rank_in_archive_order":41,"model":"ResNet-50","metrics":{"mean Corruption Error (mCE)":"76.7"},"uses_additional_data":false,"paper_date":"2019-03-28","paper":"/paper/benchmarking-neural-network-robustness-to-2","paper_url":"http://arxiv.org/abs/1903.12261v1","paper_title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","code":"https://github.com/hendrycks/robustness","n_code_links":14,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":42,"model":"DiffAUD (ConvNeXt-Tiny)","metrics":{"Top 1 Accuracy":"64.3"},"uses_additional_data":true,"paper_date":"2024-06-17","paper":"/paper/diffusion-based-adaptation-for-classification","paper_url":"https://openaccess.thecvf.com/content/CVPR2024W/NTIRE/html/Daultani_Diffusion-Based_Adaptation_for_Classification_of_Unknown_Degraded_Images_CVPRW_2024_paper.html","paper_title":"Diffusion-Based Adaptation for Classification of Unknown Degraded Images","code":"https://github.com/dineshdaultani/DiffAUD","n_code_links":1,"syntology":null},{"rank_in_archive_order":43,"model":"DiffAUD (Swin-Tiny)","metrics":{"Top 1 Accuracy":"61"},"uses_additional_data":true,"paper_date":"2024-06-17","paper":"/paper/diffusion-based-adaptation-for-classification","paper_url":"https://openaccess.thecvf.com/content/CVPR2024W/NTIRE/html/Daultani_Diffusion-Based_Adaptation_for_Classification_of_Unknown_Degraded_Images_CVPRW_2024_paper.html","paper_title":"Diffusion-Based Adaptation for Classification of Unknown Degraded Images","code":"https://github.com/dineshdaultani/DiffAUD","n_code_links":1,"syntology":null},{"rank_in_archive_order":44,"model":"ViT-B/16-SAM","metrics":{"Top 1 Accuracy":"56.5"},"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},{"rank_in_archive_order":45,"model":"ResNet-152x2-SAM","metrics":{"Top 1 Accuracy":"55"},"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":46,"model":"DiffAUD (ResNet-50)","metrics":{"Top 1 Accuracy":"52.1"},"uses_additional_data":true,"paper_date":"2024-06-17","paper":"/paper/diffusion-based-adaptation-for-classification","paper_url":"https://openaccess.thecvf.com/content/CVPR2024W/NTIRE/html/Daultani_Diffusion-Based_Adaptation_for_Classification_of_Unknown_Degraded_Images_CVPRW_2024_paper.html","paper_title":"Diffusion-Based Adaptation for Classification of Unknown Degraded Images","code":"https://github.com/dineshdaultani/DiffAUD","n_code_links":1,"syntology":null},{"rank_in_archive_order":47,"model":"Mixer-B/8-SAM","metrics":{"Top 1 Accuracy":"48.9"},"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}],"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":24,"rows_with_any_sample_ran":18,"distinct_papers_with_graph_line":14,"distinct_papers_with_any_sample_ran":12,"samples_over_distinct_papers":{"n_ran":248,"n_unverified":155,"n_samples":403,"n_pointer_only_licence":127,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":330,"n_unverified":253,"n_samples":583,"n_pointer_only_licence":163,"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"}}}