mlsanityData to 7 Oct 2026

Understanding data augmentation for classification: when to warp?

arXiv 1609.08764 ↗First posted 28 Sep 2016cs.CVcited by 74

Not on the map. Why?

Abstract (arXiv)

In this paper we investigate the benefit of augmenting data with synthetically created samples when training a machine learning classifier. Two approaches for creating additional training samples are data warping, which generates additional samples through transformations applied in the data-space, and synthetic over-sampling, which creates additional samples in feature-space. We experimentally evaluate the benefits of data augmentation for a convolutional backpropagation-trained neural network, a convolutional support vector machine and a convolutional extreme learning machine classifier, using the standard MNIST handwritten digit dataset. We found that while it is possible to perform generic augmentation in feature-space, if plausible transforms for the data are known then augmentation in data-space provides a greater benefit for improving performance and reducing overfitting.

Key facts. Cited by 74 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Sep 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 16; 2023: 21; 2024: 10; 2025: 11; 2026: 1.

74 papers.

Sort:

By area:

  1. 2021A Survey on Data Augmentation for Text Classificationcited by 111
  2. 2023On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigmcited by 107
  3. 2022A Comprehensive Survey of Image Augmentation Techniques for Deep Learningcited by 95
  4. 2022Synthetic Data -- what, why and how?cited by 66
  5. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  6. 2021How to avoid machine learning pitfalls: a guide for academic researcherscited by 34
  7. 2022A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learningcited by 23
  8. 2023Image Data Augmentation Approaches: A Comprehensive Survey and Future directionscited by 23
  9. 2022SEIL: Simulation-augmented Equivariant Imitation Learningcited by 22
  10. 2024Real Risks of Fake Data: Synthetic Data, Diversity-Washing and Consent Circumventioncited by 21
  11. 2023Fine-grained Recognition with Learnable Semantic Data Augmentationcited by 17
  12. 2022Practical Recommendations for Replay-based Continual Learning Methodscited by 16
38 more
  1. 2022Dimensionless machine learning: Imposing exact units equivariancecited by 16
  2. 2022Boomerang: Local sampling on image manifolds using diffusion modelscited by 16
  3. 2023SaGess: Sampling Graph Denoising Diffusion Model for Scalable Graph Generationcited by 13
  4. 2022CAD2Render: A Modular Toolkit for GPU-accelerated Photorealistic Synthetic Data Generation for the Manufacturing Industrycited by 10
  5. 2023Beyond Known Reality: Exploiting Counterfactual Explanations for Medical Researchcited by 9
  6. 2021Can Question Generation Debias Question Answering Models? A Case Study on Question-Context Lexical Overlapcited by 8
  7. 2021Solving the Class Imbalance Problem Using a Counterfactual Method for Data Augmentationcited by 8
  8. 2022Adversarially Robust Models may not Transfer Better: Sufficient Conditions for Domain Transferability from the View of Regularizationcited by 8
  9. 2023EEG Synthetic Data Generation Using Probabilistic Diffusion Modelscited by 8
  10. 2025Recursive Learning Without Collapse: A Weighting-Based Stabilization Frameworkcited by 8
  11. 2021Influence-guided Data Augmentation for Neural Tensor Completioncited by 7
  12. 2022Invariance encoding in sliced-Wasserstein space for image classification with limited training datacited by 7
  13. 2023Dream to Adapt: Meta Reinforcement Learning by Latent Context Imagination and MDP Imaginationcited by 6
  14. 2021The Age of Correlated Features in Supervised Learning based Forecastingcited by 5
  15. 2021A Review on Edge Analytics: Issues, Challenges, Opportunities, Promises, Future Directions, and Applicationscited by 5
  16. 2023Mask Conditional Synthetic Satellite Imagerycited by 4
  17. 2022Data Augmentation for Depression Detection Using Skeleton-Based Gait Informationcited by 3
  18. 2022Generative Adversarial Networks for Image Augmentation in Agriculture: A Systematic Reviewcited by 3
  19. 2022Weakly-supervised segmentation using inherently-explainable classification models and their application to brain tumour classificationcited by 3
  20. 2023Towards Open Federated Learning Platforms: Survey and Vision from Technical and Legal Perspectivescited by 3
  21. 2023AI Hazard Management: A framework for the systematic management of root causes for AI riskscited by 3
  22. 2024Test-Time Augmentation Meets Variational Bayescited by 3
  23. 2025Synthetic Data Generation for Augmenting Small Samplescited by 3
  24. 2025FastFlow: Early Yet Robust Network Flow Classification using the Minimal Number of Time-Series Packetscited by 3
  25. 2025CONCORD: Concept-Informed Diffusion for Dataset Distillationcited by 3
  26. 2022Deep Cross-Modality and Resolution Graph Integration for Universal Brain Connectivity Mapping and Augmentationcited by 2
  27. 2023LatentAugment: Data Augmentation via Guided Manipulation of GAN's Latent Spacecited by 2
  28. 2024Color-S4L: Self-supervised Semi-supervised Learning with Image Colorizationcited by 2
  29. 2024D4: Text-guided diffusion model-based domain adaptive data augmentation for vineyard shoot detectioncited by 2
  30. 2024An Experimental Study on Data Augmentation Techniques for Named Entity Recognition on Low-Resource Domainscited by 2
  31. 2025An Analysis of Causal Effect Estimation using Outcome Invariant Data Augmentationcited by 2
  32. 2021Meta-learning for skin cancer detection using Deep Learning Techniquescited by 1
  33. 2021FSER: Deep Convolutional Neural Networks for Speech Emotion Recognitioncited by 1
  34. 2021Multi-Domain Balanced Sampling Improves Out-of-Distribution Generalization of Chest X-ray Pathology Prediction Modelscited by 1
  35. 2023Qualitative Data Augmentation for Performance Prediction in VLSI circuitscited by 1
  36. 2023Open-set Face Recognition with Neural Ensemble, Maximal Entropy Loss and Feature Augmentationcited by 1
  37. 2023A transfer learning approach with convolutional neural network for Face Mask Detectioncited by 1
  38. 2024Predicting the Skies: A Novel Model for Flight-Level Passenger Traffic Forecastingcited by 1

50 most cited of 74 All 74 (JSON)