{"url":"/dataset/kuzushiji-mnist","name":"Kuzushiji-MNIST","full_name":null,"description_markdown":"Kuzushiji-MNIST is a drop-in replacement for the MNIST dataset (28x28 grayscale, 70,000 images). Since MNIST restricts us to 10 classes, the authors chose one character to represent each of the 10 rows of Hiragana when creating Kuzushiji-MNIST. Kuzushiji is a Japanese cursive writing style.\r\n\r\nSource: [Deep Learning for Classical Japanese Literature](/paper/deep-learning-for-classical-japanese)\r\nImage Source: [https://github.com/rois-codh/kmnist](https://github.com/rois-codh/kmnist)","description_withheld":null,"homepage":"https://github.com/rois-codh/kmnist","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/deep-learning-for-classical-japanese","title":"Deep Learning for Classical Japanese Literature","first_author":"Tarin Clanuwat","url":null},"license":{"name":"CC BY-SA 4.0","url":"https://creativecommons.org/licenses/by-sa/4.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Classification","url":"/task/image-classification","datasets_with_task":"/datasets/task/image-classification"},{"name":"Fine-Grained Image Classification","url":"/task/fine-grained-image-classification","datasets_with_task":"/datasets/task/fine-grained-image-classification"}],"languages":[{"name":"Japanese","url":"/datasets/language/japanese"}],"variants":["Kuzushiji-MNIST"],"data_loaders":[{"repo":"https://github.com/activeloopai/Hub","url":"https://docs.activeloop.ai/datasets/kmnist","frameworks":["tf","pytorch"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/kmnist","frameworks":["tf","jax"]},{"repo":"https://github.com/rois-codh/kmnist","url":"https://github.com/rois-codh/kmnist","frameworks":[]}],"num_papers_in_archive":97,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-classification-on-kuzushiji-mnist","task":"Image Classification","dataset_variant":"Kuzushiji-MNIST","rows":26,"metrics":["Accuracy","Error","Trainable Parameters"],"first_row_in_archive_order":{"model":"KMNIST-Tiny","paper":"/paper/efficient-global-neural-architecture-search","metrics":{"Accuracy":"99.35","Trainable Parameters":"420000"},"code_links":[{"title":"siddikui/Efficient-Macro-Micro-NAS","url":"https://github.com/siddikui/Efficient-Macro-Micro-NAS"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/fine-grained-image-classification-on-1","task":"Fine-Grained Image Classification","dataset_variant":"Kuzushiji-MNIST","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"VGG-5","paper":"/paper/progressivespinalnet-architecture-for-fc","metrics":{"Accuracy":"98.98"},"code_links":[{"title":"praveenchopra/ProgressiveSpinalNet","url":"https://github.com/praveenchopra/ProgressiveSpinalNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/efficient-global-neural-architecture-search","title":"Efficient Global Neural Architecture Search","date":"2025-02-08","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/learning-local-discrete-features-in","title":"Learning local discrete features in explainable-by-design convolutional neural networks","date":"2024-10-31","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improved-efficient-capsule-network-for","title":"Improved efficient capsule network for Kuzushiji-MNIST benchmark dataset classification","date":"2023-12-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cnn-filter-db-an-empirical-investigation-of","title":"CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters","date":"2022-03-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/progressivespinalnet-architecture-for-fc","title":"ProgressiveSpinalNet architecture for FC layers","date":"2021-03-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/toward-understanding-supervised","title":"Toward Understanding Supervised Representation Learning with RKHS and GAN","date":"2021-01-01","rows_on_this_dataset":9,"code_links":0,"syntology":null},{"paper":"/paper/spinalnet-deep-neural-network-with-gradual-1","title":"SpinalNet: Deep Neural Network with Gradual Input","date":"2020-07-07","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/multi-complementary-and-unlabeled-learning","title":"Multi-Complementary and Unlabeled Learning for Arbitrary Losses and Models","date":"2020-01-13","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/kercnns-biologically-inspired-lateral","title":"KerCNNs: biologically inspired lateral connections for classification of corrupted images","date":"2019-10-18","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/context-aware-multipath-networks","title":"Context-Aware Multipath Networks","date":"2019-07-26","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/the-convolutional-tsetlin-machine","title":"The Convolutional Tsetlin Machine","date":"2019-05-23","rows_on_this_dataset":1,"code_links":9,"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/a-comprehensive-study-of-imagenet-pre","title":"A Comprehensive Study of ImageNet Pre-Training for Historical Document Image Analysis","date":"2019-05-22","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/training-neural-networks-with-local-error","title":"Training Neural Networks with Local Error Signals","date":"2019-01-20","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/deep-learning-for-classical-japanese","title":"Deep Learning for Classical Japanese Literature","date":"2018-12-03","rows_on_this_dataset":1,"code_links":10,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":2,"samples_unverified":9,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/complementary-label-learning-for-arbitrary","title":"Complementary-Label Learning for Arbitrary Losses and Models","date":"2018-10-10","rows_on_this_dataset":1,"code_links":1,"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/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":"2026-09-24T18:15:14+00:00","samples_harvested":47,"samples_ran":30,"samples_unverified":17,"pointer_only_for_licence":15,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/identity-mappings-in-deep-residual-networks","title":"Identity Mappings in Deep Residual Networks","date":"2016-03-16","rows_on_this_dataset":1,"code_links":54,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":25,"samples_ran":3,"samples_unverified":22,"pointer_only_for_licence":1,"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":5,"samples_harvested":90,"samples_ran":35,"samples_unverified":55,"pointer_only_for_licence":17,"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."}