{"url":"/dataset/inaturalist","name":"iNaturalist","full_name":null,"description_markdown":"The iNaturalist 2017 dataset (iNat) contains 675,170 training and validation images from 5,089 natural fine-grained categories. Those categories belong to 13 super-categories including Plantae (Plant), Insecta (Insect), Aves (Bird), Mammalia (Mammal), and so on. The iNat dataset is highly imbalanced with dramatically different number of images per category. For example, the largest super-category “Plantae (Plant)” has 196,613 images from 2,101 categories; whereas the smallest super-category “Protozoa” only has 381 images from 4 categories.\r\n\r\nSource: [Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning](https://arxiv.org/abs/1806.06193)\r\nImage Source: [https://github.com/visipedia/inat_comp/tree/master/2017](https://github.com/visipedia/inat_comp/tree/master/2017)","description_withheld":null,"homepage":"https://github.com/visipedia/inat_comp/tree/master/2017","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-inaturalist-species-classification-and","title":"The iNaturalist Species Classification and Detection Dataset","first_author":"Grant Van Horn","url":null},"license":{"name":"Custom (non-commercial)","url":"https://github.com/visipedia/inat_comp/tree/master/2017#terms-of-use"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Classification","url":"/task/image-classification","datasets_with_task":"/datasets/task/image-classification"},{"name":"Image Generation","url":"/task/image-generation","datasets_with_task":"/datasets/task/image-generation"},{"name":"Few-Shot Image Classification","url":"/task/few-shot-image-classification","datasets_with_task":"/datasets/task/few-shot-image-classification"},{"name":"Image Retrieval","url":"/task/image-retrieval","datasets_with_task":"/datasets/task/image-retrieval"},{"name":"Fine-Grained Image Classification","url":"/task/fine-grained-image-classification","datasets_with_task":"/datasets/task/fine-grained-image-classification"},{"name":"Long-tail Learning","url":"/task/long-tail-learning","datasets_with_task":"/datasets/task/long-tail-learning"},{"name":"Test Agnostic Long-Tailed Learning","url":"/task/test-agnostic-long-tailed-learning","datasets_with_task":"/datasets/task/test-agnostic-long-tailed-learning"}],"languages":[],"variants":["iNat2021-mini","iNat2021","iNaturalist Fine-Grained Geolocation","iNaturalist 2018 - 5-shot","iNaturalist 2018 - 1-shot","iNaturalist 2018 - 10-shot","iNaturalist 2019","iNaturalist 2018","iNaturalist (227-way multi-shot)","iNaturalist"],"data_loaders":[{"repo":"https://github.com/pytorch/vision","url":"https://pytorch.org/vision/stable/generated/torchvision.datasets.INaturalist.html","frameworks":["pytorch"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/i_naturalist2017","frameworks":["tf","jax"]},{"repo":"https://github.com/visipedia/inat_comp","url":"https://github.com/visipedia/inat_comp","frameworks":[]}],"num_papers_in_archive":603,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-classification-on-inaturalist-2018","task":"Image Classification","dataset_variant":"iNaturalist 2018","rows":60,"metrics":["Top-1 Accuracy","Number of params"],"first_row_in_archive_order":{"model":"OmniVec2","paper":"/paper/omnivec2-a-novel-transformer-based-network","metrics":{"Top-1 Accuracy":"94.6"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/long-tail-learning-on-inaturalist-2018","task":"Long-tail Learning","dataset_variant":"iNaturalist 2018","rows":43,"metrics":["Top-1 Accuracy"],"first_row_in_archive_order":{"model":"LIFT (ViT-L/14@336px)","paper":"/paper/parameter-efficient-long-tailed-recognition","metrics":{"Top-1 Accuracy":"87.4%"},"code_links":[{"title":"shijxcs/lift","url":"https://github.com/shijxcs/lift"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-classification-on-inaturalist-2019","task":"Image Classification","dataset_variant":"iNaturalist 2019","rows":22,"metrics":["Top-1 Accuracy","Number of params"],"first_row_in_archive_order":{"model":"Hiera-H (448px)","paper":"/paper/hiera-a-hierarchical-vision-transformer","metrics":{"Top-1 Accuracy":"88.5"},"code_links":[{"title":"huggingface/pytorch-image-models","url":"https://github.com/huggingface/pytorch-image-models"},{"title":"facebookresearch/hiera","url":"https://github.com/facebookresearch/hiera"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/hiera"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-classification-on-inaturalist","task":"Image Classification","dataset_variant":"iNaturalist","rows":19,"metrics":["Top 1 Accuracy","Top 5 Accuracy","Top 3 Error","Overall"],"first_row_in_archive_order":{"model":"AIMv2-3B (448 res)","paper":"/paper/multimodal-autoregressive-pre-training-of","metrics":{"Top 1 Accuracy":"85.9"},"code_links":[{"title":"apple/ml-aim","url":"https://github.com/apple/ml-aim"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-retrieval-on-inaturalist","task":"Image Retrieval","dataset_variant":"iNaturalist","rows":10,"metrics":["R@1","R@16","R@32","R@5"],"first_row_in_archive_order":{"model":"Unicom+ViT-L@336px","paper":"/paper/unicom-universal-and-compact-representation","metrics":{"R@1":"88.9"},"code_links":[{"title":"OML-Team/open-metric-learning","url":"https://github.com/OML-Team/open-metric-learning"},{"title":"deepglint/unicom","url":"https://github.com/deepglint/unicom"},{"title":"RocketFlash/easy_metric_learning","url":"https://github.com/RocketFlash/easy_metric_learning/tree/master/tools"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-generation-on-inaturalist-2019","task":"Image Generation","dataset_variant":"iNaturalist 2019","rows":2,"metrics":["FID"],"first_row_in_archive_order":{"model":"StyeGAN2 + NoisyTwins","paper":"/paper/noisytwins-class-consistent-and-diverse-image","metrics":{"FID":"11.46"},"code_links":[{"title":"val-iisc/NoisyTwins","url":"https://github.com/val-iisc/NoisyTwins"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/few-shot-image-classification-on-inaturalist","task":"Few-Shot Image Classification","dataset_variant":"iNaturalist (227-way multi-shot)","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"LaplacianShot","paper":"/paper/laplacian-regularized-few-shot-learning","metrics":{"Accuracy":"74.97"},"code_links":[{"title":"sicara/easy-few-shot-learning","url":"https://github.com/sicara/easy-few-shot-learning"},{"title":"imtiazziko/LaplacianShot","url":"https://github.com/imtiazziko/LaplacianShot"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/few-shot-image-classification-on-inaturalist-1","task":"Few-Shot Image Classification","dataset_variant":"iNaturalist 2018 - 1-shot","rows":1,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"MAWS (ViT-2B)","paper":"/paper/the-effectiveness-of-mae-pre-pretraining-for","metrics":{"Top 1 Accuracy":"35.5"},"code_links":[{"title":"facebookresearch/maws","url":"https://github.com/facebookresearch/maws"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/few-shot-image-classification-on-inaturalist-2","task":"Few-Shot Image Classification","dataset_variant":"iNaturalist 2018 - 5-shot","rows":1,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"MAWS (ViT-2B)","paper":"/paper/the-effectiveness-of-mae-pre-pretraining-for","metrics":{"Top 1 Accuracy":"72.8"},"code_links":[{"title":"facebookresearch/maws","url":"https://github.com/facebookresearch/maws"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/few-shot-image-classification-on-inaturalist-3","task":"Few-Shot Image Classification","dataset_variant":"iNaturalist 2018 - 10-shot","rows":1,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"MAWS (ViT-2B)","paper":"/paper/the-effectiveness-of-mae-pre-pretraining-for","metrics":{"Top 1 Accuracy":"80.3"},"code_links":[{"title":"facebookresearch/maws","url":"https://github.com/facebookresearch/maws"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/fine-grained-image-classification-on-3","task":"Fine-Grained Image Classification","dataset_variant":"iNaturalist","rows":1,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"TASN","paper":"/paper/looking-for-the-devil-in-the-details-learning","metrics":{"Top 1 Accuracy":"68.2"},"code_links":[{"title":"researchmm/tasn","url":"https://github.com/researchmm/tasn"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-classification-on-inat2021-mini","task":"Image Classification","dataset_variant":"iNat2021-mini","rows":1,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"WaveMix-256/16 (level 2)","paper":"/paper/wavemix-lite-a-resource-efficient-neural","metrics":{"Top 1 Accuracy":"61.75"},"code_links":[{"title":"pranavphoenix/WaveMix","url":"https://github.com/pranavphoenix/WaveMix"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/multimodal-autoregressive-pre-training-of","title":"Multimodal Autoregressive Pre-training of Large Vision Encoders","date":"2024-11-21","rows_on_this_dataset":5,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/adaptive-parametric-activation","title":"Adaptive Parametric Activation","date":"2024-07-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/harnessing-hierarchical-label-distribution","title":"Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail Recognition","date":"2024-05-13","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deit-lt-distillation-strikes-back-for-vision","title":"DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets","date":"2024-04-03","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/densenets-reloaded-paradigm-shift-beyond","title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","date":"2024-03-28","rows_on_this_dataset":8,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/probabilistic-contrastive-learning-for-long","title":"Probabilistic Contrastive Learning for Long-Tailed Visual Recognition","date":"2024-03-11","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":6,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-semantic-proxies-from-visual-prompts","title":"Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learning","date":"2024-02-04","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":3,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/omnivec2-a-novel-transformer-based-network","title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","date":"2024-01-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/omnivec-learning-robust-representations-with","title":"OmniVec: Learning robust representations with cross modal sharing","date":"2023-11-07","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/parameter-efficient-long-tailed-recognition","title":"Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts","date":"2023-09-18","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":5,"samples_unverified":3,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mdcs-more-diverse-experts-with-consistency","title":"MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition","date":"2023-08-19","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":7,"samples_unverified":1,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hiera-a-hierarchical-vision-transformer","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","date":"2023-06-01","rows_on_this_dataset":3,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+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/long-tailed-recognition-by-mutual-information","title":"Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels","date":"2023-05-02","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+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/unicom-universal-and-compact-representation","title":"Unicom: Universal and Compact Representation Learning for Image Retrieval","date":"2023-04-12","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":3,"samples_unverified":3,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/noisytwins-class-consistent-and-diverse-image","title":"NoisyTwins: Class-Consistent and Diverse Image Generation through StyleGANs","date":"2023-04-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/the-effectiveness-of-mae-pre-pretraining-for","title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","date":"2023-03-23","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/escaping-saddle-points-for-effective","title":"Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data","date":"2022-12-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/internimage-exploring-large-scale-vision","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","date":"2022-11-10","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+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/generalized-parametric-contrastive-learning","title":"Generalized Parametric Contrastive Learning","date":"2022-09-26","rows_on_this_dataset":5,"code_links":4,"syntology":null},{"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/improving-gans-for-long-tailed-data-through","title":"Improving GANs for Long-Tailed Data through Group Spectral Regularization","date":"2022-08-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/conviformers-convolutionally-guided-vision","title":"Conviformers: Convolutionally guided Vision Transformer","date":"2022-08-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/balanced-contrastive-learning-for-long-tailed-1","title":"Balanced Contrastive Learning for Long-Tailed Visual Recognition","date":"2022-07-19","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+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/vit-net-interpretable-vision-transformers","title":"ViT-NeT: Interpretable Vision Transformers with Neural Tree Decoder","date":"2022-07-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hierarchical-average-precision-training-for","title":"Hierarchical Average Precision Training for Pertinent Image Retrieval","date":"2022-07-05","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":6,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/wavemix-lite-a-resource-efficient-neural","title":"WaveMix: A Resource-efficient Neural Network for Image Analysis","date":"2022-05-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/on-the-eigenvalues-of-global-covariance","title":"On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition","date":"2022-05-26","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":17,"samples_ran":3,"samples_unverified":14,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mixmim-mixed-and-masked-image-modeling-for","title":"MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers","date":"2022-05-26","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/nested-collaborative-learning-for-long-tailed","title":"Nested Collaborative Learning for Long-Tailed Visual Recognition","date":"2022-03-29","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+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/long-tailed-recognition-via-weight-balancing","title":"Long-Tailed Recognition via Weight Balancing","date":"2022-03-27","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":5,"samples_unverified":9,"pointer_only_for_licence":13,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/three-things-everyone-should-know-about","title":"Three things everyone should know about Vision Transformers","date":"2022-03-18","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+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/metaformer-a-unified-meta-framework-for-fine","title":"MetaFormer: A Unified Meta Framework for Fine-Grained Recognition","date":"2022-03-05","rows_on_this_dataset":4,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":1,"samples_unverified":13,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/batchformer-learning-to-explore-sample","title":"BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning","date":"2022-03-03","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+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/retrieval-augmented-classification-for-long","title":"Retrieval Augmented Classification for Long-Tail Visual Recognition","date":"2022-02-22","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"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/revisiting-weakly-supervised-pre-training-of","title":"Revisiting Weakly Supervised Pre-Training of Visual Perception Models","date":"2022-01-20","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/omnivore-a-single-model-for-many-visual","title":"Omnivore: A Single Model for Many Visual Modalities","date":"2022-01-20","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+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/the-majority-can-help-the-minority-context","title":"The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification","date":"2021-12-01","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":3,"samples_unverified":2,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/boosting-discriminative-visual-representation","title":"Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup","date":"2021-11-30","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/targeted-supervised-contrastive-learning-for","title":"Targeted Supervised Contrastive Learning for Long-Tailed Recognition","date":"2021-11-27","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":1,"samples_unverified":13,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/vl-ltr-learning-class-wise-visual-linguistic","title":"VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition","date":"2021-11-26","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/masked-autoencoders-are-scalable-vision","title":"Masked Autoencoders Are Scalable Vision Learners","date":"2021-11-11","rows_on_this_dataset":3,"code_links":58,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":137,"samples_ran":71,"samples_unverified":66,"pointer_only_for_licence":73,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/robust-and-decomposable-average-precision-for","title":"Robust and Decomposable Average Precision for Image Retrieval","date":"2021-10-01","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/resnet-strikes-back-an-improved-training","title":"ResNet strikes back: An improved training procedure in timm","date":"2021-10-01","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/recall-k-surrogate-loss-with-large-batches","title":"Recall@k Surrogate Loss with Large Batches and Similarity Mixup","date":"2021-08-25","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":0,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/parametric-contrastive-learning","title":"Parametric Contrastive Learning","date":"2021-07-26","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/test-agnostic-long-tailed-recognition-by-test","title":"Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition","date":"2021-07-20","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+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/rsg-a-simple-but-effective-module-for","title":"RSG: A Simple but Effective Module for Learning Imbalanced Datasets","date":"2021-06-18","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+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/resmlp-feedforward-networks-for-image","title":"ResMLP: Feedforward networks for image classification with data-efficient training","date":"2021-05-07","rows_on_this_dataset":4,"code_links":19,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":2,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/class-balanced-distillation-for-long-tailed","title":"Class-Balanced Distillation for Long-Tailed Visual Recognition","date":"2021-04-12","rows_on_this_dataset":4,"code_links":3,"syntology":null},{"paper":"/paper/levit-a-vision-transformer-in-convnet-s","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","date":"2021-04-02","rows_on_this_dataset":10,"code_links":12,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":30,"samples_ran":23,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/improving-calibration-for-long-tailed-1","title":"Improving Calibration for Long-Tailed Recognition","date":"2021-04-01","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+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/going-deeper-with-image-transformers","title":"Going deeper with Image Transformers","date":"2021-03-31","rows_on_this_dataset":2,"code_links":21,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":5,"samples_unverified":6,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/distribution-alignment-a-unified-framework","title":"Distribution Alignment: A Unified Framework for Long-tail Visual Recognition","date":"2021-03-30","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/distilling-virtual-examples-for-long-tailed","title":"Distilling Virtual Examples for Long-tailed Recognition","date":"2021-03-28","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/contrastive-learning-based-hybrid-networks","title":"Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification","date":"2021-03-26","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/automix-unveiling-the-power-of-mixup","title":"AutoMix: Unveiling the Power of Mixup for Stronger Classifiers","date":"2021-03-24","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+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/metasaug-meta-semantic-augmentation-for-long","title":"MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition","date":"2021-03-23","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/incorporating-convolution-designs-into-visual","title":"Incorporating Convolution Designs into Visual Transformers","date":"2021-03-22","rows_on_this_dataset":8,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":9,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/transfg-a-transformer-architecture-for-fine","title":"TransFG: A Transformer Architecture for Fine-grained Recognition","date":"2021-03-14","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/barlow-twins-self-supervised-learning-via","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","date":"2021-03-04","rows_on_this_dataset":1,"code_links":24,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":26,"samples_ran":21,"samples_unverified":5,"pointer_only_for_licence":10,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rethinking-ranking-based-loss-functions-only","title":"Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enough","date":"2021-02-09","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/reslt-residual-learning-for-long-tailed","title":"ResLT: Residual Learning for Long-tailed Recognition","date":"2021-01-26","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":5,"samples_unverified":4,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/training-data-efficient-image-transformers","title":"Training data-efficient image transformers & distillation through attention","date":"2020-12-23","rows_on_this_dataset":1,"code_links":40,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":19,"samples_ran":12,"samples_unverified":7,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/disentangling-label-distribution-for-long","title":"Disentangling Label Distribution for Long-tailed Visual Recognition","date":"2020-12-01","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/grafit-learning-fine-grained-image","title":"Grafit: Learning fine-grained image representations with coarse labels","date":"2020-11-25","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/posterior-re-calibration-for-imbalanced","title":"Posterior Re-calibration for Imbalanced Datasets","date":"2020-10-22","rows_on_this_dataset":1,"code_links":0,"syntology":{"read_at":"2026-09-24T18:15:14+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/long-tailed-recognition-by-routing-diverse-1","title":"Long-tailed Recognition by Routing Diverse Distribution-Aware Experts","date":"2020-10-05","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+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/feature-space-augmentation-for-long-tailed","title":"Feature Space Augmentation for Long-Tailed Data","date":"2020-08-09","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/smooth-ap-smoothing-the-path-towards-large","title":"Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval","date":"2020-07-23","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+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/laplacian-regularized-few-shot-learning","title":"Laplacian Regularized Few-Shot Learning","date":"2020-06-29","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/unsupervised-learning-of-visual-features-by","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","date":"2020-06-17","rows_on_this_dataset":1,"code_links":18,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":17,"samples_ran":13,"samples_unverified":4,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rethinking-the-value-of-labels-for-improving","title":"Rethinking the Value of Labels for Improving Class-Imbalanced Learning","date":"2020-06-13","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+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/inflated-episodic-memory-with-region-self","title":"Inflated Episodic Memory With Region Self-Attention for Long-Tailed Visual Recognition","date":"2020-06-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/rethinking-class-balanced-methods-for-long","title":"Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective","date":"2020-03-24","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/spinenet-learning-scale-permuted-backbone-for","title":"SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization","date":"2019-12-10","rows_on_this_dataset":1,"code_links":13,"syntology":null},{"paper":"/paper/clusterfit-improving-generalization-of-visual","title":"ClusterFit: Improving Generalization of Visual Representations","date":"2019-12-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/decoupling-representation-and-classifier-for","title":"Decoupling Representation and Classifier for Long-Tailed Recognition","date":"2019-10-21","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+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/fixing-the-train-test-resolution-discrepancy","title":"Fixing the train-test resolution discrepancy","date":"2019-06-14","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deep-cnns-meet-global-covariance-pooling","title":"Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization","date":"2019-04-15","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":3,"samples_unverified":2,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/looking-for-the-devil-in-the-details-learning","title":"Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition","date":"2019-03-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/graph-rise-graph-regularized-image-semantic","title":"Graph-RISE: Graph-Regularized Image Semantic Embedding","date":"2019-02-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/class-balanced-loss-based-on-effective-number","title":"Class-Balanced Loss Based on Effective Number of Samples","date":"2019-01-16","rows_on_this_dataset":3,"code_links":11,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":27,"samples_ran":7,"samples_unverified":20,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/the-inaturalist-species-classification-and","title":"The iNaturalist Species Classification and Detection Dataset","date":"2017-07-20","rows_on_this_dataset":2,"code_links":21,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":52,"samples_harvested":502,"samples_ran":259,"samples_unverified":243,"pointer_only_for_licence":152,"papers_with_no_sample_that_ran":8,"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."}