mlsanityData to 7 Oct 2026

Image Classification with Small Datasets: Overview and Benchmark

arXiv 2212.12478 ↗First posted 23 Dec 2022cs.CV cs.AI cs.NEcited by 4

Not on the map. Why?

Abstract (arXiv)

Image classification with small datasets has been an active research area in the recent past. However, as research in this scope is still in its infancy, two key ingredients are missing for ensuring reliable and truthful progress: a systematic and extensive overview of the state of the art, and a common benchmark to allow for objective comparisons between published methods. This article addresses both issues. First, we systematically organize and connect past studies to consolidate a community that is currently fragmented and scattered. Second, we propose a common benchmark that allows for an objective comparison of approaches. It consists of five datasets spanning various domains (e.g., natural images, medical imagery, satellite data) and data types (RGB, grayscale, multispectral). We use this benchmark to re-evaluate the standard cross-entropy baseline and ten existing methods published between 2017 and 2021 at renowned venues. Surprisingly, we find that thorough hyper-parameter tuning on held-out validation data results in a highly competitive baseline and highlights a stunted growth of performance over the years. Indeed, only a single specialized method dating back to 2019 clearly wins our benchmark and outperforms the baseline classifier.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 45 of its 70 references that are in the map. First posted on arXiv 23 Dec 2022.

Builds on

45 of 70 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  6. 2016Wide Residual Networkscited by 3,057
  7. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  8. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  9. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  10. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  11. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,488
  12. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
33 more
  1. 2017Random Erasing Data Augmentationcited by 1,235
  2. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  3. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 657
  4. 2018Deep Visual Domain Adaptation: A Surveycited by 634
  5. 2018Do Better ImageNet Models Transfer Better?cited by 560
  6. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
  7. 2018Bag of Tricks for Image Classification with Convolutional Neural Networkscited by 430
  8. 2019Selective Kernel Networkscited by 401
  9. 2019A Comprehensive Overhaul of Feature Distillationcited by 341
  10. 2016Harmonic Networks: Deep Translation and Rotation Equivariancecited by 293
  11. 2015Bilinear CNNs for Fine-grained Visual Recognitioncited by 228
  12. 2018A System for Massively Parallel Hyperparameter Tuningcited by 201
  13. 2018Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learningcited by 174
  14. 2021Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challengescited by 143
  15. 2020On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Locationcited by 141
  16. 2019Harnessing the Power of Infinitely Wide Deep Nets on Small-data Taskscited by 87
  17. 2019Do We Train on Test Data? Purging CIFAR of Near-Duplicatescited by 61
  18. 2020A Close Look at Deep Learning with Small Datacited by 54
  19. 2020Auxiliary Learning by Implicit Differentiationcited by 45
  20. 2019Deep Learning on Small Datasets without Pre-Training using Cosine Losscited by 41
  21. 2017OL'E: Orthogonal Low-rank Embedding, A Plug and Play Geometric Loss for Deep Learningcited by 37
  22. 2017Scaling the Scattering Transform: Deep Hybrid Networkscited by 35
  23. 2018Scattering Networks for Hybrid Representation Learningcited by 33
  24. 2020Small Data, Big Decisions: Model Selection in the Small-Data Regimecited by 23
  25. 2019Generative Modeling for Small-Data Object Detectioncited by 20
  26. 2018DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classificationcited by 18
  27. 2018Guided Dropoutcited by 14
  28. 2020Distilling Visual Priors from Self-Supervised Learningcited by 13
  29. 2021VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challengescited by 11
  30. 2019Towards Learning Affine-Invariant Representations via Data-Efficient CNNscited by 10
  31. 2021Is it enough to optimize CNN architectures on ImageNet?cited by 9
  32. 2018Learning Structure and Strength of CNN Filters for Small Sample Size Trainingcited by 8
  33. 2019Harmonic Networks with Limited Training Samplescited by 7

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 2.

4 papers.

  1. 2023Lateralized Learning for Multi-Class Visual Classification Taskscited by 1
  2. 2023No Data Augmentation? Alternative Regularizations for Effective Training on Small Datasetscited by 1
  3. 2024Twin: Tuning Learning Rate and Weight Decay of Deep Homogeneous Classifiers without Validationcited by 0
  4. 2024CBPF: Filtering Poisoned Data Based on Composite Backdoor Attackcited by 0