{"url":"/dataset/cinic-10","name":"CINIC-10","full_name":"CINIC-10","description_markdown":"**CINIC-10** is a dataset for image classification. It has a total of 270,000 images, 4.5 times that of CIFAR-10. It is constructed from two different sources: ImageNet and CIFAR-10. Specifically, it was compiled as a bridge between CIFAR-10 and ImageNet. It is split into three equal subsets - train, validation, and test - each of which contain 90,000 images.\r\n\r\nSource: [Group Knowledge Transfer:Collaborative Training of Large CNNs on the Edge](https://arxiv.org/abs/2007.14513)\r\nImage Source: [https://arxiv.org/abs/1810.03505](https://arxiv.org/abs/1810.03505)","description_withheld":null,"homepage":"https://github.com/BayesWatch/cinic-10","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/cinic-10-is-not-imagenet-or-cifar-10","title":"CINIC-10 is not ImageNet or CIFAR-10","first_author":"Luke N. Darlow","url":null},"license":{"name":"Custom","url":"https://github.com/BayesWatch/cinic-10"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Classification","url":"/task/image-classification","datasets_with_task":"/datasets/task/image-classification"},{"name":"Neural Architecture Search","url":"/task/architecture-search","datasets_with_task":"/datasets/task/architecture-search"},{"name":"Sparse Learning","url":"/task/sparse-learning","datasets_with_task":"/datasets/task/sparse-learning"}],"languages":[],"variants":["CINIC-10"],"data_loaders":[{"repo":"https://github.com/BayesWatch/cinic-10","url":"https://github.com/BayesWatch/cinic-10","frameworks":["pytorch"]}],"num_papers_in_archive":197,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-classification-on-cinic-10","task":"Image Classification","dataset_variant":"CINIC-10","rows":9,"metrics":["Accuracy","FLOPS","PARAMS"],"first_row_in_archive_order":{"model":"VIT-L/16 (Spinal FC, Background)","paper":"/paper/reduction-of-class-activation-uncertainty","metrics":{"Accuracy":"95.80"},"code_links":[{"title":"dipuk0506/SpinalNet","url":"https://github.com/dipuk0506/SpinalNet"},{"title":"dipuk0506/uq","url":"https://github.com/dipuk0506/uq"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/neural-architecture-search-on-cinic-10","task":"Neural Architecture Search","dataset_variant":"CINIC-10","rows":4,"metrics":["Accuracy (%)","FLOPS","PARAMS"],"first_row_in_archive_order":{"model":"NAT-M4","paper":"/paper/neural-architecture-transfer","metrics":{"Accuracy (%)":"94.8","FLOPS":"710M","PARAMS":"9.1M"},"code_links":[{"title":"human-analysis/neural-architecture-transfer","url":"https://github.com/human-analysis/neural-architecture-transfer"},{"title":"awesomelemon/encas","url":"https://github.com/awesomelemon/encas"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/sparse-learning-on-cinic-10-1","task":"Sparse Learning","dataset_variant":"CINIC-10","rows":1,"metrics":["Sparsity"],"first_row_in_archive_order":{"model":"Resnet18","paper":"/paper/adaptive-neural-connections-for-sparsity","metrics":{"Sparsity":"92.43"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/reduction-of-class-activation-uncertainty","title":"Reduction of Class Activation Uncertainty with Background Information","date":"2023-05-05","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/efficient-adaptive-ensembling-for-image","title":"Efficient Adaptive Ensembling for Image Classification","date":"2022-06-15","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/neural-architecture-transfer","title":"Neural Architecture Transfer","date":"2020-05-12","rows_on_this_dataset":7,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/adaptive-neural-connections-for-sparsity","title":"Adaptive Neural Connections for Sparsity Learning","date":"2020-03-05","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cinic-10-is-not-imagenet-or-cifar-10","title":"CINIC-10 is not ImageNet or CIFAR-10","date":"2018-10-02","rows_on_this_dataset":4,"code_links":2,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":1,"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."}