{"url":"/dataset/tiny-imagenet","name":"Tiny ImageNet","full_name":"Tiny ImageNet","description_markdown":"**Tiny ImageNet** contains 100000 images of 200 classes (500 for each class) downsized to 64×64 colored images. Each class has 500 training images, 50 validation images and 50 test images.\r\n\r\nSource: [Embedded Encoder-Decoder in Convolutional Networks Towards Explainable AI](https://arxiv.org/abs/2007.06712)\r\nImage Source: [https://arxiv.org/pdf/1707.08819.pdf](https://arxiv.org/pdf/1707.08819.pdf)","description_withheld":null,"homepage":"https://www.kaggle.com/c/tiny-imagenet","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":null,"title":"Tiny imagenet visual recognition challenge","first_author":null,"url":"https://tiny-imagenet.herokuapp.com"},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Classification","url":"/task/image-classification","datasets_with_task":"/datasets/task/image-classification"},{"name":"Image Clustering","url":"/task/image-clustering","datasets_with_task":"/datasets/task/image-clustering"},{"name":"Conditional Image Generation","url":"/task/conditional-image-generation","datasets_with_task":"/datasets/task/conditional-image-generation"},{"name":"Self-Supervised Learning","url":"/task/self-supervised-learning","datasets_with_task":"/datasets/task/self-supervised-learning"},{"name":"Weakly-Supervised Object Localization","url":"/task/weakly-supervised-object-localization","datasets_with_task":"/datasets/task/weakly-supervised-object-localization"},{"name":"Personalized Federated Learning","url":"/task/personalized-federated-learning","datasets_with_task":"/datasets/task/personalized-federated-learning"},{"name":"Clean-label Backdoor Attack (0.05%)","url":"/task/clean-label-backdoor-attack-0-05","datasets_with_task":"/datasets/task/clean-label-backdoor-attack-0-05"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Tiny ImageNet","Tiny ImageNet Classification","Tiny-ImageNet"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Maysee/tiny-imagenet","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/activeloopai/Hub","url":"https://docs.activeloop.ai/datasets/tiny-imagenet-dataset","frameworks":["tf","pytorch"]},{"repo":"https://github.com/ensta-u2is/torch-uncertainty","url":"https://torch-uncertainty.github.io/","frameworks":["pytorch"]},{"repo":"https://github.com/fastestimator/fastestimator","url":"https://github.com/fastestimator/fastestimator","frameworks":["tf","pytorch"]},{"repo":"https://github.com/pranavphoenix/TinyImageNetLoader","url":"https://github.com/pranavphoenix/TinyImageNetLoader","frameworks":["pytorch"]},{"repo":"https://github.com/cemos-is/robust-minisets","url":"https://github.com/cemos-is/robust-minisets","frameworks":["pytorch"]}],"num_papers_in_archive":1232,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-classification-on-tiny-imagenet-1","task":"Image Classification","dataset_variant":"Tiny ImageNet Classification","rows":23,"metrics":["Validation Acc"],"first_row_in_archive_order":{"model":"Astroformer","paper":"/paper/astroformer-more-data-might-not-be-all-you","metrics":{"Validation Acc":"92.98"},"code_links":[{"title":"Rishit-dagli/Astroformer","url":"https://github.com/Rishit-dagli/Astroformer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-clustering-on-tiny-imagenet","task":"Image Clustering","dataset_variant":"Tiny-ImageNet","rows":14,"metrics":["Accuracy","NMI","ARI"],"first_row_in_archive_order":{"model":"PRO-DSC","paper":"/paper/exploring-a-principled-framework-for-deep-1","metrics":{"Accuracy":"0.698","NMI":"0.805"},"code_links":[{"title":"mengxianghan123/PRO-DSC","url":"https://github.com/mengxianghan123/PRO-DSC"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-classification-on-tiny-imagenet-2","task":"Image Classification","dataset_variant":"Tiny-ImageNet","rows":4,"metrics":["Top 1 Accuracy","Top-1 Accuracy"],"first_row_in_archive_order":{"model":"UPANets","paper":"/paper/upanets-learning-from-the-universal-pixel","metrics":{"Top 1 Accuracy":"67.67"},"code_links":[{"title":"hanktseng131415go/UPANets","url":"https://github.com/hanktseng131415go/UPANets"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/weakly-supervised-object-localization-on-tiny","task":"Weakly-Supervised Object Localization","dataset_variant":"Tiny ImageNet","rows":3,"metrics":["Top-1 Localization Accuracy"],"first_row_in_archive_order":{"model":"InfoCAM","paper":"/paper/rethinking-softmax-with-cross-entropy-neural","metrics":{"Top-1 Localization Accuracy":"43.34"},"code_links":[{"title":"ZhenyueQin/Research-Softmax-with-Mutual-Information","url":"https://github.com/ZhenyueQin/Research-Softmax-with-Mutual-Information"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/personalized-federated-learning-on-tiny","task":"Personalized Federated Learning","dataset_variant":"Tiny ImageNet","rows":2,"metrics":["ACC@5-200Clients"],"first_row_in_archive_order":{"model":"SuPerFed-MM","paper":"/paper/subspace-learning-for-personalized-federated","metrics":{"ACC@5-200Clients":"50.07"},"code_links":[{"title":"vaseline555/superfed","url":"https://github.com/vaseline555/superfed"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/conditional-image-generation-on-tiny-imagenet","task":"Conditional Image Generation","dataset_variant":"Tiny ImageNet","rows":1,"metrics":["FID","Intra-FID"],"first_row_in_archive_order":{"model":"ADC-GAN","paper":"/paper/cgans-with-auxiliary-discriminative","metrics":{"FID":"19.02","Intra-FID":"63.05"},"code_links":[{"title":"POSTECH-CVLab/PyTorch-StudioGAN","url":"https://github.com/POSTECH-CVLab/PyTorch-StudioGAN"},{"title":"houliangict/adcgan","url":"https://github.com/houliangict/adcgan"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/self-supervised-learning-on-tiny-imagenet","task":"Self-Supervised Learning","dataset_variant":"Tiny ImageNet","rows":1,"metrics":["Top-1 Accuracy"],"first_row_in_archive_order":{"model":"CorInfomax (ResNet50)","paper":"/paper/self-supervised-learning-with-an-information","metrics":{"Top-1 Accuracy":"54.86"},"code_links":[{"title":"serdarozsoy/corinfomax-ssl","url":"https://github.com/serdarozsoy/corinfomax-ssl"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/linear-attention-with-global-context-a-1","title":"Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics","date":"2025-07-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/exploring-a-principled-framework-for-deep-1","title":"Exploring a Principled Framework for Deep Subspace Clustering","date":"2025-03-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/improving-image-clustering-with-artifacts","title":"Improving Image Clustering with Artifacts Attenuation via Inference-Time Attention Engineering","date":"2024-10-07","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/astroformer-more-data-might-not-be-all-you","title":"Astroformer: More Data Might not be all you need for Classification","date":"2023-04-03","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/data-efficient-training-of-cnns-and","title":"Data-Efficient Training of CNNs and Transformers with Coresets: A Stability Perspective","date":"2023-03-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/c3-cross-instance-guided-contrastive","title":"C3: Cross-instance guided Contrastive Clustering","date":"2022-11-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/wavemix-lite-a-resource-efficient-neural-1","title":"WaveMix-Lite: A Resource-efficient Neural Network for Image Analysis","date":"2022-10-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/ocd-learning-to-overfit-with-conditional","title":"OCD: Learning to Overfit with Conditional Diffusion Models","date":"2022-10-02","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/self-supervised-learning-with-an-information","title":"Self-Supervised Learning with an Information Maximization Criterion","date":"2022-09-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-manifold-attention-for-vision","title":"Multi-manifold Attention for Vision Transformers","date":"2022-07-18","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/dlme-deep-local-flatness-manifold-embedding","title":"DLME: Deep Local-flatness Manifold Embedding","date":"2022-07-07","rows_on_this_dataset":1,"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":1,"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/vision-transformers-in-2022-an-update-on-tiny","title":"Vision Transformers in 2022: An Update on Tiny ImageNet","date":"2022-05-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/convolutional-xformers-for-vision","title":"Convolutional Xformers for Vision","date":"2022-01-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/context-aware-compilation-of-dnn-training","title":"Context-Aware Compilation of DNN Training Pipelines across Edge and Cloud","date":"2021-12-30","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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/update-in-unit-gradient","title":"Perturbated Gradients Updating within Unit Space for Deep Learning","date":"2021-10-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/subspace-learning-for-personalized-federated","title":"Connecting Low-Loss Subspace for Personalized Federated Learning","date":"2021-09-16","rows_on_this_dataset":2,"code_links":1,"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/cgans-with-auxiliary-discriminative","title":"Conditional GANs with Auxiliary Discriminative Classifier","date":"2021-07-21","rows_on_this_dataset":1,"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":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"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/spice-semantic-pseudo-labeling-for-image","title":"SPICE: Semantic Pseudo-labeling for Image Clustering","date":"2021-03-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/upanets-learning-from-the-universal-pixel","title":"UPANets: Learning from the Universal Pixel Attention Networks","date":"2021-03-15","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/information-maximization-clustering-via-multi","title":"Information Maximization Clustering via Multi-View Self-Labelling","date":"2021-03-12","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/mixmo-mixing-multiple-inputs-for-multiple","title":"MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks","date":"2021-03-10","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/contrastive-clustering","title":"Contrastive Clustering","date":"2020-09-21","rows_on_this_dataset":1,"code_links":2,"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/puzzle-mix-exploiting-saliency-and-local-1","title":"Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup","date":"2020-09-15","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/direction-concentration-learning-enhancing","title":"Direction Concentration Learning: Enhancing Congruency in Machine Learning","date":"2019-12-17","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/multi-modal-deep-clustering-unsupervised","title":"Multi-Modal Deep Clustering: Unsupervised Partitioning of Images","date":"2019-12-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rethinking-softmax-with-cross-entropy-neural","title":"Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information Estimator","date":"2019-11-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/densenet-models-for-tiny-imagenet","title":"DenseNet Models for Tiny ImageNet Classification","date":"2019-04-23","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/deep-comprehensive-correlation-mining-for","title":"Deep Comprehensive Correlation Mining for Image Clustering","date":"2019-04-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improved-techniques-for-weakly-supervised","title":"Improved Techniques For Weakly-Supervised Object Localization","date":"2018-02-22","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/deep-adaptive-image-clustering","title":"Deep Adaptive Image Clustering","date":"2017-10-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/joint-unsupervised-learning-of-deep","title":"Joint Unsupervised Learning of Deep Representations and Image Clusters","date":"2016-04-13","rows_on_this_dataset":1,"code_links":3,"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/learning-deep-features-for-discriminative","title":"Learning Deep Features for Discriminative Localization","date":"2015-12-14","rows_on_this_dataset":1,"code_links":35,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":17,"samples_ran":2,"samples_unverified":15,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/unsupervised-representation-learning-with-1","title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","date":"2015-11-19","rows_on_this_dataset":1,"code_links":258,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":219,"samples_ran":113,"samples_unverified":106,"pointer_only_for_licence":111,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/unsupervised-deep-embedding-for-clustering","title":"Unsupervised Deep Embedding for Clustering Analysis","date":"2015-11-19","rows_on_this_dataset":1,"code_links":23,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":25,"samples_ran":2,"samples_unverified":23,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/auto-encoding-variational-bayes","title":"Auto-Encoding Variational Bayes","date":"2013-12-20","rows_on_this_dataset":1,"code_links":144,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":199,"samples_ran":112,"samples_unverified":87,"pointer_only_for_licence":103,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":17,"samples_harvested":501,"samples_ran":250,"samples_unverified":251,"pointer_only_for_licence":238,"papers_with_no_sample_that_ran":5,"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."}