{"url":"/task/small-data","name":"Small Data Image Classification","slug":"small-data","description_markdown":"Supervised image classification with tens to hundreds of labeled training examples.","categories":[{"name":"Adversarial","url":"/area/adversarial"},{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":179,"papers_with_code":58,"benchmarks":12,"benchmark_tables_in_archive":12,"benchmark_tables_shown":12,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":9,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/small-data-image-classification-on-deic","slug":"small-data-image-classification-on-deic","dataset":"DEIC Benchmark","dataset_url":"/dataset/deic-benchmark","rows_in_archive":10,"metrics":["Average Balanced Accuracy (across datasets)"],"first_row_in_archive_order":{"model":"Harmonic Networks","paper_title":"Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification","paper_url":"/paper/tune-it-or-don-t-use-it-benchmarking-data","paper_date":"2021-08-30","arxiv_id":"2108.13122","code_links":[{"title":"cvjena/deic","url":"https://github.com/cvjena/deic"}],"syntology":null}},{"leaderboard":"/sota/small-data-image-classification-on-cifar-10","slug":"small-data-image-classification-on-cifar-10","dataset":"CIFAR-10, 500 Labels","dataset_url":"/dataset/cifar-10","rows_in_archive":6,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"ChimeraMix+AutoAugment","paper_title":"ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing","paper_url":"/paper/image-classification-on-small-datasets-via","paper_date":"2022-02-23","arxiv_id":"2202.11616","code_links":[{"title":"creinders/chimeramix","url":"https://github.com/creinders/chimeramix"}],"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/small-data-image-classification-on-cifair-10-1","slug":"small-data-image-classification-on-cifair-10-1","dataset":"ciFAIR-10 50 samples per class","dataset_url":"/dataset/deic-benchmark","rows_in_archive":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ChimeraMix+AutoAugment","paper_title":"ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing","paper_url":"/paper/image-classification-on-small-datasets-via","paper_date":"2022-02-23","arxiv_id":"2202.11616","code_links":[{"title":"creinders/chimeramix","url":"https://github.com/creinders/chimeramix"}],"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/small-data-image-classification-on-cifar-10-2","slug":"small-data-image-classification-on-cifar-10-2","dataset":"CIFAR-10, 100 Labels","dataset_url":"/dataset/cifar-10","rows_in_archive":5,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"ChimeraMix+AutoAugment","paper_title":"ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing","paper_url":"/paper/image-classification-on-small-datasets-via","paper_date":"2022-02-23","arxiv_id":"2202.11616","code_links":[{"title":"creinders/chimeramix","url":"https://github.com/creinders/chimeramix"}],"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/small-data-image-classification-on-cifar-10-3","slug":"small-data-image-classification-on-cifar-10-3","dataset":"CIFAR-10, 1000 Labels","dataset_url":"/dataset/cifar-10","rows_in_archive":5,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"ChimeraMix+AutoAugment","paper_title":"ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing","paper_url":"/paper/image-classification-on-small-datasets-via","paper_date":"2022-02-23","arxiv_id":"2202.11616","code_links":[{"title":"creinders/chimeramix","url":"https://github.com/creinders/chimeramix"}],"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/small-data-on-cub-200-2011-30-samples-per-1","slug":"small-data-on-cub-200-2011-30-samples-per-1","dataset":"CUB-200-2011, 30 samples per class","dataset_url":"/dataset/cub-200-2011","rows_in_archive":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GLICO","paper_title":"Generative Latent Implicit Conditional Optimization when Learning from Small Sample","paper_url":"/paper/learning-from-small-data-through-sampling-an","paper_date":"2020-03-31","arxiv_id":"2003.14297","code_links":[{"title":"IdanAzuri/glico-learning-small-sample","url":"https://github.com/IdanAzuri/glico-learning-small-sample"}],"syntology":{"n":16,"n_ran":0,"n_unverified":16,"n_pointer_only":0}}},{"leaderboard":"/sota/small-data-image-classification-on-eurosat-50","slug":"small-data-image-classification-on-eurosat-50","dataset":"EuroSAT 50 samples per class","dataset_url":"/dataset/deic-benchmark","rows_in_archive":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Harmonic Networks","paper_title":"Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification","paper_url":"/paper/tune-it-or-don-t-use-it-benchmarking-data","paper_date":"2021-08-30","arxiv_id":"2108.13122","code_links":[{"title":"cvjena/deic","url":"https://github.com/cvjena/deic"}],"syntology":null}},{"leaderboard":"/sota/small-data-image-classification-on-imagenet","slug":"small-data-image-classification-on-imagenet","dataset":"ImageNet 50 samples per class","dataset_url":"/dataset/imagenet-50-samples-per-class","rows_in_archive":3,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"Harmonic Networks","paper_title":"Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification","paper_url":"/paper/tune-it-or-don-t-use-it-benchmarking-data","paper_date":"2021-08-30","arxiv_id":"2108.13122","code_links":[{"title":"cvjena/deic","url":"https://github.com/cvjena/deic"}],"syntology":null}},{"leaderboard":"/sota/small-data-on-cifar-100-1000-labels-1","slug":"small-data-on-cifar-100-1000-labels-1","dataset":"CIFAR-100, 1000 Labels","dataset_url":"/dataset/cifar-100","rows_in_archive":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ChimeraMix+AutoAugment","paper_title":"ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing","paper_url":"/paper/image-classification-on-small-datasets-via","paper_date":"2022-02-23","arxiv_id":"2202.11616","code_links":[{"title":"creinders/chimeramix","url":"https://github.com/creinders/chimeramix"}],"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/small-data-image-classification-on-cifar10-10","slug":"small-data-image-classification-on-cifar10-10","dataset":"cifar10, 10 labels","dataset_url":"/dataset/cifar-10","rows_in_archive":2,"metrics":["% Test Accuracy"],"first_row_in_archive_order":{"model":"VAE","paper_title":"Performance Analysis of Semi-supervised Learning in the Small-data Regime using VAEs","paper_url":"/paper/performance-analysis-of-semi-supervised","paper_date":"2020-02-26","arxiv_id":"2002.12164","code_links":[{"title":"varunmannam/Papers_with_Code","url":"https://github.com/varunmannam/Papers_with_Code/tree/master/VAE_project"}],"syntology":null}},{"leaderboard":"/sota/small-data-image-classification-on-cifar-10-1","slug":"small-data-image-classification-on-cifar-10-1","dataset":"CIFAR-10, 250 Labels","dataset_url":"/dataset/cifar-10","rows_in_archive":1,"metrics":["Top-1 accuracy %"],"first_row_in_archive_order":{"model":"GLICO","paper_title":"Generative Latent Implicit Conditional Optimization when Learning from Small Sample","paper_url":"/paper/learning-from-small-data-through-sampling-an","paper_date":"2020-03-31","arxiv_id":"2003.14297","code_links":[{"title":"IdanAzuri/glico-learning-small-sample","url":"https://github.com/IdanAzuri/glico-learning-small-sample"}],"syntology":{"n":16,"n_ran":0,"n_unverified":16,"n_pointer_only":0}}},{"leaderboard":"/sota/small-data-on-cub-200-2011-5-samples-per-1","slug":"small-data-on-cub-200-2011-5-samples-per-1","dataset":"CUB-200-2011, 5 samples per class","dataset_url":"/dataset/cub-200-2011","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GLICO","paper_title":"Generative Latent Implicit Conditional Optimization when Learning from Small Sample","paper_url":"/paper/learning-from-small-data-through-sampling-an","paper_date":"2020-03-31","arxiv_id":"2003.14297","code_links":[{"title":"IdanAzuri/glico-learning-small-sample","url":"https://github.com/IdanAzuri/glico-learning-small-sample"}],"syntology":{"n":16,"n_ran":0,"n_unverified":16,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/cifar-10","name":"CIFAR-10","full_name":"CIFAR-10","num_papers_in_archive":16145},{"url":"/dataset/cifar-100","name":"CIFAR-100","full_name":"","num_papers_in_archive":9045},{"url":"/dataset/cub-200-2011","name":"CUB-200-2011","full_name":"Caltech-UCSD Birds-200-2011","num_papers_in_archive":2235},{"url":"/dataset/ucf-crime","name":"UCF-Crime","full_name":"","num_papers_in_archive":142},{"url":"/dataset/tmed","name":"TMED","full_name":"Tufts Medical Echocardiogram Dataset","num_papers_in_archive":10},{"url":"/dataset/ecoli","name":"Ecoli","full_name":null,"num_papers_in_archive":9},{"url":"/dataset/deic-benchmark","name":"DEIC Benchmark","full_name":"Data-Efficient Image Classification Benchmark","num_papers_in_archive":3},{"url":"/dataset/imagenet-50-samples-per-class","name":"ImageNet 50 samples per class","full_name":"","num_papers_in_archive":1},{"url":"/dataset/wikichurches","name":"WikiChurches","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/image-classification","name":"Image Classification"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":58,"tagged_in_all":179,"items":[{"url":"/paper/unveiling-covid-19-from-chest-x-ray-with-deep","title":"Unveiling COVID-19 from Chest X-ray with deep learning: a hurdles race with small data","date":"2020-04-11","arxiv_id":"2004.05405","repositories_listed":9,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/retina-u-net-embarrassingly-simple","title":"Retina U-Net: Embarrassingly Simple Exploitation of Segmentation Supervision for Medical Object Detection","date":"2018-11-21","arxiv_id":"1811.08661","repositories_listed":6,"syntology":null},{"url":"/paper/harnessing-the-power-of-infinitely-wide-deep-1","title":"Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks","date":"2019-10-03","arxiv_id":"1910.01663","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/learning-what-and-where-to-transfer","title":"Learning What and Where to Transfer","date":"2019-05-15","arxiv_id":"1905.05901","repositories_listed":4,"syntology":{"n":11,"n_ran":4,"n_unverified":7,"n_pointer_only":1}},{"url":"/paper/on-translation-invariance-in-cnns","title":"On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location","date":"2020-03-16","arxiv_id":"2003.07064","repositories_listed":3,"syntology":null},{"url":"/paper/bayesian-convolutional-neural-networks-with","title":"Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference","date":"2015-06-06","arxiv_id":"1506.02158","repositories_listed":3,"syntology":null},{"url":"/paper/rigid-soft-interactive-learning-for-robust","title":"Rigid-Soft Interactive Learning for Robust Grasping","date":"2020-02-29","arxiv_id":"2003.01584","repositories_listed":2,"syntology":null},{"url":"/paper/190409406","title":"DeepMoD: Deep learning for Model Discovery in noisy data","date":"2019-04-20","arxiv_id":"1904.09406","repositories_listed":2,"syntology":{"n":18,"n_ran":0,"n_unverified":18,"n_pointer_only":0}},{"url":"/paper/reproducible-evaluation-of-diffusion-mri","title":"Reproducible evaluation of diffusion MRI features for automatic classification of patients with Alzheimers disease","date":"2018-12-28","arxiv_id":"1812.11183","repositories_listed":2,"syntology":null},{"url":"/paper/cumf_sgd-fast-and-scalable-matrix","title":"CuMF_SGD: Fast and Scalable Matrix Factorization","date":"2016-10-19","arxiv_id":"1610.05838","repositories_listed":2,"syntology":null},{"url":"/paper/image-classification-with-small-datasets","title":"Image Classification With Small Datasets: Overview and Benchmark","date":"2022-05-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/image-classification-on-small-datasets-via","title":"ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing","date":"2022-02-23","arxiv_id":"2202.11616","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/torchxrayvision-a-library-of-chest-x-ray","title":"TorchXRayVision: A library of chest X-ray datasets and models","date":"2021-10-31","arxiv_id":"2111.00595","repositories_listed":1,"syntology":null},{"url":"/paper/tune-it-or-don-t-use-it-benchmarking-data","title":"Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification","date":"2021-08-30","arxiv_id":"2108.13122","repositories_listed":1,"syntology":null},{"url":"/paper/s2d2net-an-improved-approach-for-robust-steel","title":"S2D2Net: An Improved Approach For Robust Steel Surface Defects Diagnosis With Small Sample Learning","date":"2021-08-23","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/parametric-scattering-networks","title":"Parametric Scattering Networks","date":"2021-07-20","arxiv_id":"2107.09539","repositories_listed":1,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/about-explicit-variance-minimization-training","title":"About Explicit Variance Minimization: Training Neural Networks for Medical Imaging With Limited Data Annotations","date":"2021-05-28","arxiv_id":"2105.14117","repositories_listed":1,"syntology":null},{"url":"/paper/auxiliary-learning-by-implicit","title":"Auxiliary Learning by Implicit Differentiation","date":"2020-06-22","arxiv_id":"2007.02693","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/ensemble-long-short-term-memory-enlstm","title":"Ensemble long short-term memory (EnLSTM) network","date":"2020-04-26","arxiv_id":"2004.13562","repositories_listed":1,"syntology":null},{"url":"/paper/meta-meta-classification-for-one-shot","title":"Meta-Meta Classification for One-Shot Learning","date":"2020-04-17","arxiv_id":"2004.08083","repositories_listed":1,"syntology":null},{"url":"/paper/analysis-of-social-media-data-using","title":"Analysis of Social Media Data using Multimodal Deep Learning for Disaster Response","date":"2020-04-14","arxiv_id":"2004.11838","repositories_listed":1,"syntology":null},{"url":"/paper/finding-covid-19-from-chest-x-rays-using-deep","title":"Finding Covid-19 from Chest X-rays using Deep Learning on a Small Dataset","date":"2020-04-05","arxiv_id":"2004.02060","repositories_listed":1,"syntology":null},{"url":"/paper/learning-from-small-data-through-sampling-an","title":"Generative Latent Implicit Conditional Optimization when Learning from Small Sample","date":"2020-03-31","arxiv_id":"2003.14297","repositories_listed":1,"syntology":{"n":16,"n_ran":0,"n_unverified":16,"n_pointer_only":0}},{"url":"/paper/mix-n-match-ensemble-and-compositional","title":"Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning","date":"2020-03-16","arxiv_id":"2003.07329","repositories_listed":1,"syntology":{"n":12,"n_ran":5,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/unbiased-mean-teacher-for-cross-domain-object","title":"Unbiased Mean Teacher for Cross-domain Object Detection","date":"2020-03-02","arxiv_id":"2003.00707","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/compact-representation-of-uncertainty-in-1","title":"Data Structures & Algorithms for Exact Inference in Hierarchical Clustering","date":"2020-02-26","arxiv_id":"2002.11661","repositories_listed":1,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/performance-analysis-of-semi-supervised","title":"Performance Analysis of Semi-supervised Learning in the Small-data Regime using VAEs","date":"2020-02-26","arxiv_id":"2002.12164","repositories_listed":1,"syntology":null},{"url":"/paper/on-coresets-for-support-vector-machines","title":"On Coresets for Support Vector Machines","date":"2020-02-15","arxiv_id":"2002.06469","repositories_listed":1,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/incorporating-physical-constraints-in-a-deep","title":"Incorporating physical constraints in a deep probabilistic machine learning framework for coarse-graining dynamical systems","date":"2019-12-30","arxiv_id":"1912.12976","repositories_listed":1,"syntology":{"n":10,"n_ran":0,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/randomly-projected-additive-gaussian","title":"Randomly Projected Additive Gaussian Processes for Regression","date":"2019-12-30","arxiv_id":"1912.12834","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":4}}],"syntology_records":14,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}