{"url":"/dataset/cifar-fs","name":"CIFAR-FS","full_name":"CIFAR100 few-shots","description_markdown":"**CIFAR100 few-shots** (**CIFAR-FS**) is randomly sampled from CIFAR-100 (Krizhevsky & Hinton, 2009) by using the same criteria with which miniImageNet has been generated. The average inter-class similarity is sufficiently high to represent a challenge for the current state of the art. Moreover, the limited original resolution of 32×32 makes the task harder and at the same time allows fast prototyping.\r\n\r\nSource: [Bertinetto et al.](https://arxiv.org/pdf/1805.08136.pdf)\r\nImage source: [Bertinetto et al.](https://www.robots.ox.ac.uk/~luca/r2d2.html)","description_withheld":null,"homepage":"https://github.com/bertinetto/r2d2","introduced_date":"2018-05-21","introduced_date_note":null,"introduced_by":{"paper":"/paper/meta-learning-with-differentiable-closed-form","title":"Meta-learning with differentiable closed-form solvers","first_author":"Luca Bertinetto","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Few-Shot Image Classification","url":"/task/few-shot-image-classification","datasets_with_task":"/datasets/task/few-shot-image-classification"}],"languages":[],"variants":["CIFAR-FS 5-way (1-shot)","CIFAR-FS 5-way (5-shot)","CIFAR-FS"],"data_loaders":[{"repo":"https://github.com/learnables/learn2learn","url":"http://learn2learn.net","frameworks":["pytorch"]},{"repo":"https://github.com/bertinetto/r2d2","url":"https://github.com/bertinetto/r2d2","frameworks":["pytorch"]}],"num_papers_in_archive":206,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/few-shot-image-classification-on-cifar-fs-5-1","task":"Few-Shot Image Classification","dataset_variant":"CIFAR-FS 5-way (5-shot)","rows":39,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CAML [Laion-2b]","paper":"/paper/context-aware-meta-learning","metrics":{"Accuracy":"93.5"},"code_links":[{"title":"cfifty/CAML","url":"https://github.com/cfifty/CAML"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/few-shot-image-classification-on-cifar-fs-5","task":"Few-Shot Image Classification","dataset_variant":"CIFAR-FS 5-way (1-shot)","rows":38,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PT+MAP+SF+SOT (transductive)","paper":"/paper/the-self-optimal-transport-feature-transform","metrics":{"Accuracy":"89.94 "},"code_links":[{"title":"danielshalam/bpa","url":"https://github.com/danielshalam/bpa"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/geometric-mean-improves-loss-for-few-shot","title":"Geometric Mean Improves Loss For Few-Shot Learning","date":"2025-01-24","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/the-balanced-pairwise-affinities-feature","title":"The Balanced-Pairwise-Affinities Feature Transform","date":"2024-06-25","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/context-aware-meta-learning","title":"Context-Aware Meta-Learning","date":"2023-10-17","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":16,"samples_ran":5,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/adaptive-dimension-reduction-and-variational","title":"Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification","date":"2022-09-18","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/rethinking-generalization-in-few-shot-1","title":"Rethinking Generalization in Few-Shot Classification","date":"2022-06-15","rows_on_this_dataset":2,"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":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pushing-the-limits-of-simple-pipelines-for","title":"Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference","date":"2022-04-15","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":19,"samples_ran":6,"samples_unverified":13,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/the-self-optimal-transport-feature-transform","title":"The Self-Optimal-Transport Feature Transform","date":"2022-04-06","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/attribute-surrogates-learning-and-spectral","title":"Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning","date":"2022-03-17","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/easy-ensemble-augmented-shot-y-shaped","title":"EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients","date":"2022-01-24","rows_on_this_dataset":8,"code_links":3,"syntology":null},{"paper":"/paper/squeezing-backbone-feature-distributions-to","title":"Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning","date":"2021-10-18","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/sparse-spatial-transformers-for-few-shot","title":"Sparse Spatial Transformers for Few-Shot Learning","date":"2021-09-27","rows_on_this_dataset":2,"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/relational-embedding-for-few-shot","title":"Relational Embedding for Few-Shot Classification","date":"2021-08-22","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":11,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bridging-multi-task-learning-and-meta","title":"Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation","date":"2021-06-16","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":1,"samples_unverified":9,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/exploring-complementary-strengths-of","title":"Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning","date":"2021-03-01","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/transfer-learning-based-few-shot","title":"Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network","date":"2021-02-09","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/sill-net-feature-augmentation-with-separated","title":"Sill-Net: Feature Augmentation with Separated Illumination Representation","date":"2021-02-06","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/shallow-bayesian-meta-learning-for-real-world","title":"Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition","date":"2021-01-08","rows_on_this_dataset":2,"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":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/constellation-nets-for-few-shot-learning","title":"Constellation Nets for Few-Shot Learning","date":"2021-01-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/pseudo-shots-few-shot-learning-with-auxiliary","title":"Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks","date":"2020-12-13","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/match-them-up-visually-explainable-few-shot","title":"Match Them Up: Visually Explainable Few-shot Image Classification","date":"2020-11-25","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/region-comparison-network-for-interpretable","title":"Region Comparison Network for Interpretable Few-shot Image Classification","date":"2020-09-08","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/complementing-representation-deficiency-in","title":"Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach","date":"2020-07-21","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/self-supervised-knowledge-distillation-for","title":"Self-supervised Knowledge Distillation for Few-shot Learning","date":"2020-06-17","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/leveraging-the-feature-distribution-in","title":"Leveraging the Feature Distribution in Transfer-based Few-Shot Learning","date":"2020-06-06","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":26,"samples_ran":10,"samples_unverified":16,"pointer_only_for_licence":11,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/adaptive-subspaces-for-few-shot-learning","title":"Adaptive Subspaces for Few-Shot Learning","date":"2020-06-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/empirical-bayes-transductive-meta-learning-1","title":"Empirical Bayes Transductive Meta-Learning with Synthetic Gradients","date":"2020-04-27","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":3,"samples_unverified":2,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/instance-credibility-inference-for-few-shot","title":"Instance Credibility Inference for Few-Shot Learning","date":"2020-03-26","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/task-augmentation-by-rotating-for-meta","title":"Task Augmentation by Rotating for Meta-Learning","date":"2020-02-08","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/fast-and-generalized-adaptation-for-few-shot","title":"Generalized Adaptation for Few-Shot Learning","date":"2019-11-25","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/charting-the-right-manifold-manifold-mixup","title":"Charting the Right Manifold: Manifold Mixup for Few-shot Learning","date":"2019-07-28","rows_on_this_dataset":2,"code_links":8,"syntology":null},{"paper":"/paper/meta-learning-with-differentiable-convex","title":"Meta-Learning with Differentiable Convex Optimization","date":"2019-04-07","rows_on_this_dataset":2,"code_links":7,"syntology":null},{"paper":"/paper/learning-to-compare-relation-network-for-few","title":"Learning to Compare: Relation Network for Few-Shot Learning","date":"2017-11-16","rows_on_this_dataset":1,"code_links":13,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"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":12,"samples_harvested":109,"samples_ran":47,"samples_unverified":62,"pointer_only_for_licence":23,"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."}