mlsanityData to 7 Oct 2026

The Effectiveness of Data Augmentation in Image Classification using Deep Learning

arXiv 1712.04621 ↗First posted 13 Dec 2017cs.CVcited by 368

Not on the map. Why?

Abstract (arXiv)

In this paper, we explore and compare multiple solutions to the problem of data augmentation in image classification. Previous work has demonstrated the effectiveness of data augmentation through simple techniques, such as cropping, rotating, and flipping input images. We artificially constrain our access to data to a small subset of the ImageNet dataset, and compare each data augmentation technique in turn. One of the more successful data augmentations strategies is the traditional transformations mentioned above. We also experiment with GANs to generate images of different styles. Finally, we propose a method to allow a neural net to learn augmentations that best improve the classifier, which we call neural augmentation. We discuss the successes and shortcomings of this method on various datasets.

Key facts. Cited by 368 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Dec 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 87; 2022: 85; 2023: 73; 2024: 68; 2025: 40; 2026: 15.

368 papers.

Sort:

By area:

  1. 2021Deep Neural Networks and Tabular Data: A Surveycited by 489
  2. 2021Deep Long-Tailed Learning: A Surveycited by 416
  3. 2023Effective Data Augmentation With Diffusion Modelscited by 282
  4. 2022Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detectioncited by 172
  5. 2021SCARF: Self-Supervised Contrastive Learning using Random Feature Corruptioncited by 151
  6. 2023Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuningcited by 150
  7. 2023A Comprehensive Survey of Dataset Distillationcited by 114
  8. 2021Inducing Causal Structure for Interpretable Neural Networkscited by 107
  9. 2021Contrastive Learning with Stronger Augmentationscited by 100
  10. 2022Image Data Augmentation for Deep Learning: A Surveycited by 96
  11. 2022EnvEdit: Environment Editing for Vision-and-Language Navigationcited by 83
  12. 2022VeLO: Training Versatile Learned Optimizers by Scaling Upcited by 57
38 more
  1. 2023GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generationcited by 56
  2. 2021Neural Data Augmentation via Example Extrapolationcited by 54
  3. 2022Hybrid Relation Guided Set Matching for Few-shot Action Recognitioncited by 49
  4. 2022Vision-Based Manipulators Need to Also See from Their Handscited by 46
  5. 2022Large Scale Transfer Learning for Differentially Private Image Classificationcited by 40
  6. 2021Tractable Regularization of Probabilistic Circuitscited by 39
  7. 2021Effective Evaluation of Deep Active Learning on Image Classification Taskscited by 37
  8. 2021Mine Your Own vieW: Self-Supervised Learning Through Across-Sample Predictioncited by 36
  9. 2022Long-Tailed Class Incremental Learningcited by 36
  10. 2021Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classificationcited by 35
  11. 2023Self-supervised Monocular Depth Estimation: Let's Talk About The Weathercited by 33
  12. 2021Performance of a Geometric Deep Learning Pipeline for HL-LHC Particle Trackingcited by 29
  13. 2021CLCC: Contrastive Learning for Color Constancycited by 29
  14. 2024Learning Universal Predictorscited by 29
  15. 2021Dense Unsupervised Learning for Video Segmentationcited by 26
  16. 2024Closing the Gap between TD Learning and Supervised Learning -- A Generalisation Point of Viewcited by 26
  17. 2021GaNDLF: A Generally Nuanced Deep Learning Framework for Scalable End-to-End Clinical Workflows in Medical Imagingcited by 25
  18. 2021A Deep Variational Approach to Clustering Survival Datacited by 25
  19. 2023SyncFusion: Multimodal Onset-synchronized Video-to-Audio Foley Synthesiscited by 24
  20. 2021Scale-aware Automatic Augmentation for Object Detectioncited by 23
  21. 2021Achieving Model Robustness through Discrete Adversarial Trainingcited by 23
  22. 2021Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developmentscited by 23
  23. 2023Image Data Augmentation Approaches: A Comprehensive Survey and Future directionscited by 23
  24. 2024Understanding Test-Time Augmentationcited by 23
  25. 2021A novel multiple instance learning framework for COVID-19 severity assessment via data augmentation and self-supervised learningcited by 19
  26. 2023Anatomy-aware and acquisition-agnostic joint registration with SynthMorphcited by 19
  27. 2022RGB no more: Minimally-decoded JPEG Vision Transformerscited by 18
  28. 2023Synthetic Augmentation with Large-scale Unconditional Pre-trainingcited by 18
  29. 2023Pre-training on Synthetic Driving Data for Trajectory Predictioncited by 18
  30. 2021LARGE: Latent-Based Regression through GAN Semanticscited by 17
  31. 2022Data Augmentation vs. Equivariant Networks: A Theory of Generalization on Dynamics Forecastingcited by 17
  32. 2023SurvivalGAN: Generating Time-to-Event Data for Survival Analysiscited by 17
  33. 2023Fine-grained Recognition with Learnable Semantic Data Augmentationcited by 17
  34. 2024Semantically Controllable Augmentations for Generalizable Robot Learningcited by 17
  35. 2021Co-Correcting: Noise-tolerant Medical Image Classification via mutual Label Correctioncited by 16
  36. 2023Distributionally Robust Post-hoc Classifiers under Prior Shiftscited by 16
  37. 2022Learning Instance-Specific Augmentations by Capturing Local Invariancescited by 15
  38. 2023AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimationcited by 15

50 most cited of 368 All 368 (JSON)