mlsanityData to 7 Oct 2026

Image Data Augmentation for Deep Learning: A Survey

arXiv 2204.08610 ↗First posted 19 Apr 2022cs.CVcited by 96

Not on the map. Why?

Abstract (arXiv)

Deep learning has achieved remarkable results in many computer vision tasks. Deep neural networks typically rely on large amounts of training data to avoid overfitting. However, labeled data for real-world applications may be limited. By improving the quantity and diversity of training data, data augmentation has become an inevitable part of deep learning model training with image data. As an effective way to improve the sufficiency and diversity of training data, data augmentation has become a necessary part of successful application of deep learning models on image data. In this paper, we systematically review different image data augmentation methods. We propose a taxonomy of reviewed methods and present the strengths and limitations of these methods. We also conduct extensive experiments with various data augmentation methods on three typical computer vision tasks, including semantic segmentation, image classification and object detection. Finally, we discuss current challenges faced by data augmentation and future research directions to put forward some useful research guidance.

Key facts. Cited by 96 papers in the map (data through 7 Oct 2026). Builds on 39 of its 66 references that are in the map. First posted on arXiv 19 Apr 2022.

Builds on

39 of 66 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2016Densely Connected Convolutional Networkscited by 6,691
  6. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  7. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  8. 2016Wide Residual Networkscited by 3,057
  9. 2016Improved Techniques for Training GANscited by 2,938
  10. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  11. 2016Pyramid Scene Parsing Networkcited by 2,472
  12. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
27 more
  1. 2014Conditional Generative Adversarial Netscited by 2,152
  2. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  3. 2017Random Erasing Data Augmentationcited by 1,235
  4. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  5. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  6. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  7. 2020Image Segmentation Using Deep Learning: A Surveycited by 659
  8. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  9. 2018Deep Learning for Generic Object Detection: A Surveycited by 392
  10. 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 368
  11. 2019GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyondcited by 331
  12. 2019Population Based Augmentation: Efficient Learning of Augmentation Policy Schedulescited by 153
  13. 2017Dataset Augmentation in Feature Spacecited by 124
  14. 2020GridMask Data Augmentationcited by 123
  15. 2019Image Classification with Deep Learning in the Presence of Noisy Labels: A Surveycited by 101
  16. 2018Data Augmentation by Pairing Samples for Images Classificationcited by 96
  17. 2017Shake-Shake regularizationcited by 87
  18. 2020On Feature Normalization and Data Augmentationcited by 71
  19. 2020FeatMatch: Feature-Based Augmentation for Semi-Supervised Learningcited by 57
  20. 2019Interlaced Sparse Self-Attention for Semantic Segmentationcited by 53
  21. 2020KeepAugment: A Simple Information-Preserving Data Augmentation Approachcited by 52
  22. 2020Natural Language Processing Advancements By Deep Learning: A Surveycited by 50
  23. 2019Online Hyper-parameter Learning for Auto-Augmentation Strategycited by 38
  24. 2018Hide-and-Seek: A Data Augmentation Technique for Weakly-Supervised Localization and Beyondcited by 36
  25. 2020Improving Auto-Augment via Augmentation-Wise Weight Sharingcited by 28
  26. 2019A Survey on Face Data Augmentationcited by 23
  27. 2020FenceMask: A Data Augmentation Approach for Pre-extracted Image Featurescited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 29; 2024: 25; 2025: 26; 2026: 10.

96 papers.

Sort:

By area:

  1. 2022Expanding Small-Scale Datasets with Guided Imaginationcited by 61
  2. 2025Diffusion Beats Autoregressive in Data-Constrained Settingscited by 61
  3. 2024A survey of synthetic data augmentation methods in computer visioncited by 34
  4. 2024A Survey on Data Augmentation in Large Model Eracited by 31
  5. 2023Advancements in Point Cloud Data Augmentation for Deep Learning: A Surveycited by 24
  6. 2022A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learningcited by 23
  7. 2023Image Data Augmentation Approaches: A Comprehensive Survey and Future directionscited by 23
  8. 2022Boomerang: Local sampling on image manifolds using diffusion modelscited by 16
  9. 2023Semantic-Guided Generative Image Augmentation Method with Diffusion Models for Image Classificationcited by 16
  10. 2023Fused Gromov-Wasserstein Graph Mixup for Graph-level Classificationscited by 15
  11. 2023NNG-Mix: Improving Semi-supervised Anomaly Detection with Pseudo-anomaly Generationcited by 14
  12. 2024EntAugment: Entropy-Driven Adaptive Data Augmentation Framework for Image Classificationcited by 13
38 more
  1. 2023fAIlureNotes: Supporting Designers in Understanding the Limits of AI Models for Computer Vision Taskscited by 10
  2. 2023Molecule Joint Auto-Encoding: Trajectory Pretraining with 2D and 3D Diffusioncited by 10
  3. 2023A Survey on Self-Supervised Representation Learningcited by 9
  4. 2023Distilling Out-of-Distribution Robustness from Vision-Language Foundation Modelscited by 9
  5. 2023What makes a good data augmentation for few-shot unsupervised image anomaly detection?cited by 8
  6. 2024SWIFT: Semantic Watermarking for Image Forgery Thwartingcited by 8
  7. 2025VACoT: Rethinking Visual Data Augmentation with VLMscited by 8
  8. 2024AdaAugment: A Tuning-Free and Adaptive Approach to Enhance Data Augmentationcited by 7
  9. 2023Non-adversarial Robustness of Deep Learning Methods for Computer Visioncited by 6
  10. 2023KERMIT: Knowledge Graph Completion of Enhanced Relation Modeling with Inverse Transformationcited by 6
  11. 2023Data Optimization in Deep Learning: A Surveycited by 6
  12. 2025When Dynamic Data Selection Meets Data Augmentationcited by 6
  13. 20253D Skeleton-Based Action Recognition: A Reviewcited by 6
  14. 2023Domain Generalization by Rejecting Extreme Augmentationscited by 5
  15. 2025AimTS: Augmented Series and Image Contrastive Learning for Time Series Classificationcited by 5
  16. 2022A Machine Learning Enhanced Approach for Automated Sunquake Detection in Acoustic Emission Mapscited by 4
  17. 2023A tailored Handwritten-Text-Recognition System for Medieval Latincited by 4
  18. 2024Revealing the Two Sides of Data Augmentation: An Asymmetric Distillation-based Win-Win Solution for Open-Set Recognitioncited by 4
  19. 2024Cooperative learning of Pl@ntNet's Artificial Intelligence algorithm: how does it work and how can we improve it?cited by 4
  20. 2024Enriching Information and Preserving Semantic Consistency in Expanding Curvilinear Object Segmentation Datasetscited by 4
  21. 2024Enhancing Few-Shot Image Classification through Learnable Multi-Scale Embedding and Attention Mechanismscited by 4
  22. 2023CeCNN: Copula-enhanced convolutional neural networks in joint prediction of refraction error and axial length based on ultra-widefield fundus imagescited by 3
  23. 2024How Important are Data Augmentations to Close the Domain Gap for Object Detection in Orbit?cited by 3
  24. 2025Contrastive Visual Data Augmentationcited by 3
  25. 2025Zero Shot Domain Adaptive Semantic Segmentation by Synthetic Data Generation and Progressive Adaptationcited by 3
  26. 2025Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networkscited by 3
  27. 2023Unleash Model Potential: Bootstrapped Meta Self-supervised Learningcited by 2
  28. 2024Colorful Cutout: Enhancing Image Data Augmentation with Curriculum Learningcited by 2
  29. 2024Learning from Offline Foundation Features with Tensor Augmentationscited by 2
  30. 2024Beyond Knowledge Silos: Task Fingerprinting for Democratization of Medical Imaging AIcited by 2
  31. 2025Hierarchical Deep Feature Fusion and Ensemble Learning for Enhanced Brain Tumor MRI Classificationcited by 2
  32. 2022Efficient Neural Net Approaches in Metal Casting Defect Detectioncited by 1
  33. 2023Mpox-AISM: AI-Mediated Super Monitoring for Mpox and Like-Mpoxcited by 1
  34. 2023Brain MRI Segmentation using Template-Based Training and Visual Perception Augmentationcited by 1
  35. 2023Prediction of Diblock Copolymer Morphology via Machine Learningcited by 1
  36. 2023On the Efficacy of Multi-scale Data Samplers for Vision Applicationscited by 1
  37. 2023A Note on Generalization in Variational Autoencoders: How Effective Is Synthetic Data & Overparameterization?cited by 1
  38. 2024You Only Need Half: Boosting Data Augmentation by Using Partial Contentcited by 1

50 most cited of 96 All 96 (JSON)