{"url":"/sota/few-shot-image-classification-on-cub-200-5-1","task":{"name":"Few-Shot Image Classification","url":"/task/few-shot-image-classification","note":null},"dataset":{"name":"CUB 200 5-way 1-shot","url":"/dataset/cub-200-2011"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Few-Shot Image Classification** is a computer vision task that involves training machine learning models to classify images into predefined categories using only a few labeled examples of each category (typically < 6 examples). The goal is to enable models to recognize and classify new images with minimal supervision and limited data, without having to train on large datasets. (typically < 6 examples)\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Learning Embedding Adaptation for Few-Shot Learning](https://github.com/Sha-Lab/FEAT) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher"}},"counts":{"rows":36,"rows_with_code":33,"rows_with_paper_page":36,"rows_dated":36,"rows_using_additional_data":3},"rows":[{"rank_in_archive_order":1,"model":"PT+MAP+SF+SOT (transductive)","metrics":{"Accuracy":"95.80"},"uses_additional_data":false,"paper_date":"2022-04-06","paper":"/paper/the-self-optimal-transport-feature-transform","paper_url":"https://arxiv.org/abs/2204.03065v1","paper_title":"The Self-Optimal-Transport Feature Transform","code":"https://github.com/danielshalam/bpa","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"CAML [Laion-2b]","metrics":{"Accuracy":"95.8"},"uses_additional_data":true,"paper_date":"2023-10-17","paper":"/paper/context-aware-meta-learning","paper_url":"https://arxiv.org/abs/2310.10971v2","paper_title":"Context-Aware Meta-Learning","code":"https://github.com/cfifty/CAML","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":11,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"PT+MAP+SF+BPA (transductive)","metrics":{"Accuracy":"95.80"},"uses_additional_data":false,"paper_date":"2024-06-25","paper":"/paper/the-balanced-pairwise-affinities-feature","paper_url":"https://arxiv.org/abs/2407.01467v1","paper_title":"The Balanced-Pairwise-Affinities Feature Transform","code":"https://github.com/danielshalam/bpa","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"PT+MAP+SF (transductive)","metrics":{"Accuracy":"95.48"},"uses_additional_data":false,"paper_date":"2021-05-11","paper":"/paper/few-shot-learning-by-integrating-spatial-and","paper_url":"https://arxiv.org/abs/2105.05348v2","paper_title":"Few-Shot Learning by Integrating Spatial and Frequency Representation","code":"https://github.com/xiangyu8/PT-MAP-sf","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"PEMnE-BMS*","metrics":{"Accuracy":"94.78"},"uses_additional_data":true,"paper_date":"2021-10-18","paper":"/paper/squeezing-backbone-feature-distributions-to","paper_url":"https://arxiv.org/abs/2110.09446v1","paper_title":"Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning","code":"https://github.com/yhu01/bms","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"Illumination Augmentation","metrics":{"Accuracy":"94.73"},"uses_additional_data":false,"paper_date":"2021-02-06","paper":"/paper/sill-net-feature-augmentation-with-separated","paper_url":"https://arxiv.org/abs/2102.03539v3","paper_title":"Sill-Net: Feature Augmentation with Separated Illumination Representation","code":"https://github.com/lanfenghuanyu/Sill-Net","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"LST+MAP","metrics":{"Accuracy":"91.68"},"uses_additional_data":false,"paper_date":"2021-02-09","paper":"/paper/transfer-learning-based-few-shot","paper_url":"https://arxiv.org/abs/2102.05176v2","paper_title":"Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network","code":"https://github.com/ctom2/latent-space-transform","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"PT+MAP","metrics":{"Accuracy":"91.55%"},"uses_additional_data":false,"paper_date":"2020-06-06","paper":"/paper/leveraging-the-feature-distribution-in","paper_url":"https://arxiv.org/abs/2006.03806v3","paper_title":"Leveraging the Feature Distribution in Transfer-based Few-Shot Learning","code":"https://github.com/sicara/easy-few-shot-learning","n_code_links":6,"syntology":{"n_ran":10,"n_unverified":16,"n_samples":26,"n_pointer_only_licence":11}},{"rank_in_archive_order":9,"model":"EASY 3xResNet12 (transductive)","metrics":{"Accuracy":"90.56"},"uses_additional_data":false,"paper_date":"2022-01-24","paper":"/paper/easy-ensemble-augmented-shot-y-shaped","paper_url":"https://arxiv.org/abs/2201.09699v2","paper_title":"EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients","code":"https://github.com/ybendou/easy","n_code_links":3,"syntology":null},{"rank_in_archive_order":10,"model":"EASY 4xResNet12 (transductive)","metrics":{"Accuracy":"90.5"},"uses_additional_data":false,"paper_date":"2022-01-24","paper":"/paper/easy-ensemble-augmented-shot-y-shaped","paper_url":"https://arxiv.org/abs/2201.09699v2","paper_title":"EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients","code":"https://github.com/ybendou/easy","n_code_links":3,"syntology":null},{"rank_in_archive_order":11,"model":"BAVARDAGE","metrics":{"Accuracy":"90.42"},"uses_additional_data":false,"paper_date":"2022-09-18","paper":"/paper/adaptive-dimension-reduction-and-variational","paper_url":"https://arxiv.org/abs/2209.08527v1","paper_title":"Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"ICI","metrics":{"Accuracy":"89.58"},"uses_additional_data":false,"paper_date":"2020-03-26","paper":"/paper/instance-credibility-inference-for-few-shot","paper_url":"https://arxiv.org/abs/2003.11853v2","paper_title":"Instance Credibility Inference for Few-Shot Learning","code":"https://github.com/Yikai-Wang/ICI-FSL","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"Transfer+SGC","metrics":{"Accuracy":"88.35%"},"uses_additional_data":false,"paper_date":"2020-01-27","paper":"/paper/exploiting-unsupervised-inputs-for-accurate","paper_url":"https://arxiv.org/abs/2001.09849v4","paper_title":"Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classification","code":"https://github.com/yhu01/transfer-sgc","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"ESPT","metrics":{"Accuracy":"85.45"},"uses_additional_data":false,"paper_date":"2023-04-26","paper":"/paper/espt-a-self-supervised-episodic-spatial","paper_url":"https://arxiv.org/abs/2304.13287v1","paper_title":"ESPT: A Self-Supervised Episodic Spatial Pretext Task for Improving Few-Shot Learning","code":"https://github.com/whut-yirong/espt","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":15,"model":"TDM","metrics":{"Accuracy":"84.36"},"uses_additional_data":false,"paper_date":"2022-07-04","paper":"/paper/task-discrepancy-maximization-for-fine-1","paper_url":"https://arxiv.org/abs/2207.01376v1","paper_title":"Task Discrepancy Maximization for Fine-grained Few-Shot Classification","code":"https://github.com/leesb7426/cvpr2022-task-discrepancy-maximization-for-fine-grained-few-shot-classification","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":16,"model":"BD-CSPN + ESFR (ResNet-18)","metrics":{"Accuracy":"82.68"},"uses_additional_data":false,"paper_date":"2021-06-22","paper":"/paper/unsupervised-embedding-adaptation-via-early","paper_url":"https://arxiv.org/abs/2106.11486v1","paper_title":"Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classification","code":"https://github.com/movinghoon/ESFR","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":17,"model":"TIM-GD","metrics":{"Accuracy":"82.2%"},"uses_additional_data":false,"paper_date":"2020-08-25","paper":"/paper/transductive-information-maximization-for-few","paper_url":"https://arxiv.org/abs/2008.11297v3","paper_title":"Transductive Information Maximization For Few-Shot Learning","code":"https://github.com/sicara/easy-few-shot-learning","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":6,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"LaplacianShot","metrics":{"Accuracy":"80.96"},"uses_additional_data":false,"paper_date":"2020-06-29","paper":"/paper/laplacian-regularized-few-shot-learning","paper_url":"https://arxiv.org/abs/2006.15486","paper_title":"Laplacian Regularized Few-Shot Learning","code":"https://github.com/sicara/easy-few-shot-learning","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":7,"n_samples":12,"n_pointer_only_licence":7}},{"rank_in_archive_order":19,"model":"S2M2R","metrics":{"Accuracy":"80.68"},"uses_additional_data":false,"paper_date":"2019-07-28","paper":"/paper/charting-the-right-manifold-manifold-mixup","paper_url":"https://arxiv.org/abs/1907.12087v4","paper_title":"Charting the Right Manifold: Manifold Mixup for Few-shot Learning","code":"https://github.com/ShuoYang-1998/Few_Shot_Distribution_Calibration","n_code_links":8,"syntology":null},{"rank_in_archive_order":20,"model":"RENet","metrics":{"Accuracy":"79.49"},"uses_additional_data":false,"paper_date":"2021-08-22","paper":"/paper/relational-embedding-for-few-shot","paper_url":"https://arxiv.org/abs/2108.09666v1","paper_title":"Relational Embedding for Few-Shot Classification","code":"https://github.com/dahyun-kang/renet","n_code_links":1,"syntology":{"n_ran":11,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":21,"model":"Ours","metrics":{"Accuracy":"79.12"},"uses_additional_data":false,"paper_date":"2020-10-07","paper":"/paper/variational-transfer-learning-for-fine","paper_url":"https://arxiv.org/abs/2010.03255v3","paper_title":"Variational Feature Disentangling for Fine-Grained Few-Shot Classification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":22,"model":"EASY 3xResNet12 (inductive)","metrics":{"Accuracy":"78.56"},"uses_additional_data":false,"paper_date":"2022-01-24","paper":"/paper/easy-ensemble-augmented-shot-y-shaped","paper_url":"https://arxiv.org/abs/2201.09699v2","paper_title":"EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients","code":"https://github.com/ybendou/easy","n_code_links":3,"syntology":null},{"rank_in_archive_order":23,"model":"EASY 4xResNet12 (inductive)","metrics":{"Accuracy":"77.97"},"uses_additional_data":false,"paper_date":"2022-01-24","paper":"/paper/easy-ensemble-augmented-shot-y-shaped","paper_url":"https://arxiv.org/abs/2201.09699v2","paper_title":"EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients","code":"https://github.com/ybendou/easy","n_code_links":3,"syntology":null},{"rank_in_archive_order":24,"model":"AmdimNet","metrics":{"Accuracy":"77.09"},"uses_additional_data":false,"paper_date":"2019-11-14","paper":"/paper/self-supervised-learning-for-few-shot-image","paper_url":"https://arxiv.org/abs/1911.06045v3","paper_title":"Self-Supervised Learning For Few-Shot Image Classification","code":"https://github.com/Alibaba-AAIG/SSL-FEW-SHOT","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":25,"model":"MergedNet-Max","metrics":{"Accuracy":"75.34"},"uses_additional_data":false,"paper_date":"2022-10-14","paper":"/paper/mergednet-a-simple-approach-for-one-shot","paper_url":"https://doi.org/10.1016/j.neucom.2022.08.070","paper_title":"MergedNET: A simple approach for one-shot learning in siamese networks based on similarity layers","code":"https://github.com/Amotica/MergedNET","n_code_links":1,"syntology":null},{"rank_in_archive_order":26,"model":"Neg-Margin","metrics":{"Accuracy":"72.66"},"uses_additional_data":false,"paper_date":"2020-03-26","paper":"/paper/negative-margin-matters-understanding-margin","paper_url":"https://arxiv.org/abs/2003.12060v1","paper_title":"Negative Margin Matters: Understanding Margin in Few-shot Classification","code":"https://github.com/bl0/negative-margin.few-shot","n_code_links":1,"syntology":null},{"rank_in_archive_order":27,"model":"DKT + BNCosSim","metrics":{"Accuracy":"72.27"},"uses_additional_data":false,"paper_date":"2019-10-11","paper":"/paper/deep-kernel-transfer-in-gaussian-processes","paper_url":"https://arxiv.org/abs/1910.05199v4","paper_title":"Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels","code":"https://github.com/BayesWatch/deep-kernel-transfer","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":28,"model":"Self-Critique and Adapt + High-End MAML++","metrics":{"Accuracy":"70.46"},"uses_additional_data":false,"paper_date":"2019-05-24","paper":"/paper/learning-to-learn-by-self-critique","paper_url":"https://arxiv.org/abs/1905.10295v6","paper_title":"Learning to learn via Self-Critique","code":"https://github.com/AntreasAntoniou/Learning_to_Learn_via_Self-Critique","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":11,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":29,"model":"Delta-encoder","metrics":{"Accuracy":"69.8"},"uses_additional_data":false,"paper_date":"2018-06-12","paper":"/paper/delta-encoder-an-effective-sample-synthesis","paper_url":"http://arxiv.org/abs/1806.04734v3","paper_title":"Delta-encoder: an effective sample synthesis method for few-shot object recognition","code":"https://github.com/EliSchwartz/DeltaEncoder","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"feat (ProtoNet)","metrics":{"Accuracy":"68.65"},"uses_additional_data":false,"paper_date":"2018-12-10","paper":"/paper/learning-embedding-adaptation-for-few-shot","paper_url":"https://arxiv.org/abs/1812.03664v6","paper_title":"Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions","code":"https://github.com/sicara/easy-few-shot-learning","n_code_links":6,"syntology":null},{"rank_in_archive_order":31,"model":"High-End MAML++","metrics":{"Accuracy":"67.48"},"uses_additional_data":false,"paper_date":"2019-05-24","paper":"/paper/learning-to-learn-by-self-critique","paper_url":"https://arxiv.org/abs/1905.10295v6","paper_title":"Learning to learn via Self-Critique","code":"https://github.com/AntreasAntoniou/Learning_to_Learn_via_Self-Critique","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":11,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":32,"model":"HyperShot","metrics":{"Accuracy":"66.13"},"uses_additional_data":false,"paper_date":"2022-03-21","paper":"/paper/hypershot-few-shot-learning-by-kernel","paper_url":"https://arxiv.org/abs/2203.11378v1","paper_title":"HyperShot: Few-Shot Learning by Kernel HyperNetworks","code":"https://github.com/gmum/few-shot-hypernets-public","n_code_links":1,"syntology":null},{"rank_in_archive_order":33,"model":"RS-FSL","metrics":{"Accuracy":"65.66"},"uses_additional_data":true,"paper_date":"2021-04-26","paper":"/paper/rich-semantics-improve-few-shot-learning","paper_url":"https://arxiv.org/abs/2104.12709v2","paper_title":"Rich Semantics Improve Few-shot Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":34,"model":"Hyperbolic ProtoNet","metrics":{"Accuracy":"60.52"},"uses_additional_data":false,"paper_date":"2019-04-03","paper":"/paper/hyperbolic-image-embeddings","paper_url":"https://arxiv.org/abs/1904.02239v2","paper_title":"Hyperbolic Image Embeddings","code":"https://github.com/KhrulkovV/hyperbolic-image-embeddings","n_code_links":3,"syntology":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":35,"model":"DN4-DA (k=1)","metrics":{"Accuracy":"53.15"},"uses_additional_data":false,"paper_date":"2019-03-28","paper":"/paper/revisiting-local-descriptor-based-image-to","paper_url":"http://arxiv.org/abs/1903.12290v2","paper_title":"Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning","code":"https://github.com/WenbinLee/DN4","n_code_links":1,"syntology":null},{"rank_in_archive_order":36,"model":"Relation Net","metrics":{"Accuracy":"50.44"},"uses_additional_data":false,"paper_date":"2017-11-16","paper":"/paper/learning-to-compare-relation-network-for-few","paper_url":"http://arxiv.org/abs/1711.06025v2","paper_title":"Learning to Compare: Relation Network for Few-Shot Learning","code":"https://github.com/sicara/easy-few-shot-learning","n_code_links":13,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":1}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,795 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":14,"rows_with_any_sample_ran":12,"distinct_papers_with_graph_line":13,"distinct_papers_with_any_sample_ran":11,"samples_over_distinct_papers":{"n_ran":47,"n_unverified":59,"n_samples":106,"n_pointer_only_licence":24,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":49,"n_unverified":70,"n_samples":119,"n_pointer_only_licence":24,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}