{"url":"/dataset/imagenet-a","name":"ImageNet-A","full_name":null,"description_markdown":"The **ImageNet-A** dataset consists of real-world, unmodified, and naturally occurring examples that are misclassified by ResNet models.\r\n\r\nSource: [On Robustness and Transferability of Convolutional Neural Networks](https://arxiv.org/abs/2007.08558)\r\nImage Source: [https://github.com/hendrycks/natural-adv-examples](https://github.com/hendrycks/natural-adv-examples)","description_withheld":null,"homepage":"https://github.com/hendrycks/natural-adv-examples","introduced_date":"2019-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/natural-adversarial-examples","title":"Natural Adversarial Examples","first_author":"Dan Hendrycks","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Unsupervised Domain Adaptation","url":"/task/unsupervised-domain-adaptation","datasets_with_task":"/datasets/task/unsupervised-domain-adaptation"},{"name":"Domain Generalization","url":"/task/domain-generalization","datasets_with_task":"/datasets/task/domain-generalization"},{"name":"Zero-Shot Transfer Image Classification","url":"/task/zero-shot-transfer-image-classification","datasets_with_task":"/datasets/task/zero-shot-transfer-image-classification"},{"name":"Prompt Engineering","url":"/task/prompt-engineering","datasets_with_task":"/datasets/task/prompt-engineering"},{"name":"Adversarial Robustness","url":"/task/adversarial-robustness","datasets_with_task":"/datasets/task/adversarial-robustness"}],"languages":[],"variants":["ImageNet-A"],"data_loaders":[{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/imagenet_a","frameworks":["tf","jax"]},{"repo":"https://github.com/hendrycks/natural-adv-examples","url":"https://github.com/hendrycks/natural-adv-examples","frameworks":["pytorch"]},{"repo":"https://github.com/ensta-u2is/torch-uncertainty","url":"https://torch-uncertainty.github.io/","frameworks":["pytorch"]}],"num_papers_in_archive":431,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/domain-generalization-on-imagenet-a","task":"Domain Generalization","dataset_variant":"ImageNet-A","rows":39,"metrics":["Top-1 accuracy %","Number of params"],"first_row_in_archive_order":{"model":"Model soups (BASIC-L)","paper":"/paper/model-soups-averaging-weights-of-multiple","metrics":{"Top-1 accuracy %":"94.17"},"code_links":[{"title":"mlfoundations/model-soups","url":"https://github.com/mlfoundations/model-soups"},{"title":"Burf/ModelSoups","url":"https://github.com/Burf/ModelSoups"},{"title":"facebookresearch/ModelRatatouille","url":"https://github.com/facebookresearch/ModelRatatouille"},{"title":"hwk0702/keras2torch","url":"https://github.com/hwk0702/keras2torch/tree/main/Computer_Vision/Model_Soup"},{"title":"flowritecom/flow-merge","url":"https://github.com/flowritecom/flow-merge"},{"title":"shallowlearn/sportsreid","url":"https://github.com/shallowlearn/sportsreid"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-5","task":"Zero-Shot Transfer Image Classification","dataset_variant":"ImageNet-A","rows":13,"metrics":["Accuracy (Private)","Accuracy (Public)"],"first_row_in_archive_order":{"model":"CoCa","paper":"/paper/coca-contrastive-captioners-are-image-text","metrics":{"Accuracy (Private)":"90.2"},"code_links":[{"title":"mlfoundations/open_clip","url":"https://github.com/mlfoundations/open_clip"},{"title":"facebookresearch/multimodal","url":"https://github.com/facebookresearch/multimodal"},{"title":"lucidrains/CoCa-pytorch","url":"https://github.com/lucidrains/CoCa-pytorch"},{"title":"amitakamath/whatsup_vlms","url":"https://github.com/amitakamath/whatsup_vlms"},{"title":"amitakamath/hard_positives","url":"https://github.com/amitakamath/hard_positives"},{"title":"Chaolei98/FreeZAD","url":"https://github.com/Chaolei98/FreeZAD"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/prompt-engineering-on-imagenet-a","task":"Prompt Engineering","dataset_variant":"ImageNet-A","rows":9,"metrics":["Top-1 accuracy %"],"first_row_in_archive_order":{"model":"POMP","paper":"/paper/prompt-pre-training-with-twenty-thousand-1","metrics":{"Top-1 accuracy %":"51.6"},"code_links":[{"title":"amazon-science/prompt-pretraining","url":"https://github.com/amazon-science/prompt-pretraining"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/adversarial-robustness-on-imagenet-a","task":"Adversarial Robustness","dataset_variant":"ImageNet-A","rows":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"DeiT-S (AdamW, Cosine)","paper":"/paper/are-transformers-more-robust-than-cnns","metrics":{"Accuracy":"12.2"},"code_links":[{"title":"ytongbai/ViTs-vs-CNNs","url":"https://github.com/ytongbai/ViTs-vs-CNNs"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-domain-adaptation-on-imagenet-a","task":"Unsupervised Domain Adaptation","dataset_variant":"ImageNet-A","rows":1,"metrics":["Top 1 Error"],"first_row_in_archive_order":{"model":"EfficientNet-L2 NoisyStudent + RPL","paper":"/paper/adapting-imagenet-scale-models-to-complex","metrics":{"Top 1 Error":"14.8"},"code_links":[{"title":"bethgelab/robustness","url":"https://github.com/bethgelab/robustness"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/mmrl-multi-modal-representation-learning-for","title":"MMRL: Multi-Modal Representation Learning for Vision-Language Models","date":"2025-03-11","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hpt-hierarchically-prompting-vision-language","title":"HPT++: Hierarchically Prompting Vision-Language Models with Multi-Granularity Knowledge Generation and Improved Structure Modeling","date":"2024-08-27","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/eva-clip-18b-scaling-clip-to-18-billion","title":"EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters","date":"2024-02-06","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":6,"samples_ran":1,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fully-attentional-networks-with-self-emerging-1","title":"Fully Attentional Networks with Self-emerging Token Labeling","date":"2024-01-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/internvl-scaling-up-vision-foundation-models","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","date":"2023-12-21","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-hierarchical-prompt-with-structured","title":"Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models","date":"2023-12-11","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":7,"samples_ran":3,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/transnext-robust-foveal-visual-perception-for","title":"TransNeXt: Robust Foveal Visual Perception for Vision Transformers","date":"2023-11-28","rows_on_this_dataset":4,"code_links":4,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":5,"samples_ran":5,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/distilling-out-of-distribution-robustness-1","title":"Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models","date":"2023-11-02","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/self-regulating-prompts-foundational-model","title":"Self-regulating Prompts: Foundational Model Adaptation without Forgetting","date":"2023-07-13","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":21,"samples_ran":17,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/consistency-guided-prompt-learning-for-vision","title":"Consistency-guided Prompt Learning for Vision-Language Models","date":"2023-06-01","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":7,"samples_ran":3,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/prompt-pre-training-with-twenty-thousand-1","title":"Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition","date":"2023-04-10","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":7,"samples_ran":5,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/your-diffusion-model-is-secretly-a-zero-shot","title":"Your Diffusion Model is Secretly a Zero-Shot Classifier","date":"2023-03-28","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/eva-clip-improved-training-techniques-for","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","date":"2023-03-27","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/scaling-vision-transformers-to-22-billion","title":"Scaling Vision Transformers to 22 Billion Parameters","date":"2023-02-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/context-aware-robust-fine-tuning","title":"Context-Aware Robust Fine-Tuning","date":"2022-11-29","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/altclip-altering-the-language-encoder-in-clip","title":"AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities","date":"2022-11-12","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":11,"samples_ran":10,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/metaformer-baselines-for-vision","title":"MetaFormer Baselines for Vision","date":"2022-10-24","rows_on_this_dataset":8,"code_links":8,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/maple-multi-modal-prompt-learning","title":"MaPLe: Multi-modal Prompt Learning","date":"2022-10-06","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":6,"samples_ran":4,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/enhance-the-visual-representation-via","title":"Enhance the Visual Representation via Discrete Adversarial Training","date":"2022-09-16","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":11,"samples_ran":10,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-continual-development-methodology-for-large","title":"A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems","date":"2022-09-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pali-a-jointly-scaled-multilingual-language","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","date":"2022-09-14","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":4,"samples_ran":2,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/sequencer-deep-lstm-for-image-classification","title":"Sequencer: Deep LSTM for Image Classification","date":"2022-05-04","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":9,"samples_ran":4,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/coca-contrastive-captioners-are-image-text","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","date":"2022-05-04","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":17,"samples_ran":10,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/understanding-the-robustness-in-vision","title":"Understanding The Robustness in Vision Transformers","date":"2022-04-26","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/model-soups-averaging-weights-of-multiple","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","date":"2022-03-10","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":17,"samples_ran":8,"samples_unverified":9,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/conditional-prompt-learning-for-vision","title":"Conditional Prompt Learning for Vision-Language Models","date":"2022-03-10","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":6,"samples_ran":4,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/vision-models-are-more-robust-and-fair-when","title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","date":"2022-02-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-convnet-for-the-2020s","title":"A ConvNet for the 2020s","date":"2022-01-10","rows_on_this_dataset":1,"code_links":54,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":80,"samples_ran":57,"samples_unverified":23,"pointer_only_for_licence":11,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pyramid-adversarial-training-improves-vit","title":"Pyramid Adversarial Training Improves ViT Performance","date":"2021-11-30","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/combined-scaling-for-zero-shot-transfer","title":"Combined Scaling for Zero-shot Transfer Learning","date":"2021-11-19","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/lit-zero-shot-transfer-with-locked-image-text","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","date":"2021-11-15","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/masked-autoencoders-are-scalable-vision","title":"Masked Autoencoders Are Scalable Vision Learners","date":"2021-11-11","rows_on_this_dataset":1,"code_links":58,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":137,"samples_ran":86,"samples_unverified":51,"pointer_only_for_licence":73,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/are-transformers-more-robust-than-cnns","title":"Are Transformers More Robust Than CNNs?","date":"2021-11-10","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/global-filter-networks-for-image","title":"Global Filter Networks for Image Classification","date":"2021-07-01","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":10,"samples_ran":6,"samples_unverified":4,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rethinking-the-design-principles-of-robust","title":"Towards Robust Vision Transformer","date":"2021-05-17","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/adapting-imagenet-scale-models-to-complex","title":"If your data distribution shifts, use self-learning","date":"2021-04-27","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-transferable-visual-models-from","title":"Learning Transferable Visual Models From Natural Language Supervision","date":"2021-02-26","rows_on_this_dataset":2,"code_links":82,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":20,"samples_ran":16,"samples_unverified":4,"pointer_only_for_licence":16,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/scaling-up-visual-and-vision-language","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","date":"2021-02-11","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":10,"samples_ran":8,"samples_unverified":2,"pointer_only_for_licence":9,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/on-feature-normalization-and-data","title":"On Feature Normalization and Data Augmentation","date":"2020-02-25","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":14,"samples_ran":5,"samples_unverified":9,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/natural-adversarial-examples","title":"Natural Adversarial Examples","date":"2019-07-16","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/cutmix-regularization-strategy-to-train","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","date":"2019-05-13","rows_on_this_dataset":1,"code_links":30,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":24,"samples_ran":17,"samples_unverified":7,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/imagenet-trained-cnns-are-biased-towards","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","date":"2018-11-29","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mixup-beyond-empirical-risk-minimization","title":"mixup: Beyond Empirical Risk Minimization","date":"2017-10-25","rows_on_this_dataset":1,"code_links":71,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":47,"samples_ran":32,"samples_unverified":15,"pointer_only_for_licence":15,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/improved-regularization-of-convolutional","title":"Improved Regularization of Convolutional Neural Networks with Cutout","date":"2017-08-15","rows_on_this_dataset":1,"code_links":28,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":24,"samples_ran":21,"samples_unverified":3,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deep-residual-learning-for-image-recognition","title":"Deep Residual Learning for Image Recognition","date":"2015-12-10","rows_on_this_dataset":1,"code_links":484,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":377,"samples_ran":242,"samples_unverified":135,"pointer_only_for_licence":187,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":33,"samples_harvested":903,"samples_ran":586,"samples_unverified":317,"pointer_only_for_licence":330,"papers_with_no_sample_that_ran":2,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}