# Understanding data augmentation for classification: when to warp?

arXiv: https://arxiv.org/abs/1609.08764 · HTML: https://mlsanity.com/paper/1609.08764/

## Key facts

- Cited by 74 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2016.

## Built on by (most cited first, 30 of 74)

- [A Survey on Data Augmentation for Text Classification](https://mlsanity.com/paper/2107.03158/) (2021)
- [On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm](https://mlsanity.com/paper/2312.03526/) (2023)
- [A Comprehensive Survey of Image Augmentation Techniques for Deep Learning](https://mlsanity.com/paper/2205.01491/) (2022)
- [Synthetic Data -- what, why and how?](https://mlsanity.com/paper/2205.03257/) (2022)
- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [How to avoid machine learning pitfalls: a guide for academic researchers](https://mlsanity.com/paper/2108.02497/) (2021)
- [A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning](https://mlsanity.com/paper/2210.04561/) (2022)
- [SEIL: Simulation-augmented Equivariant Imitation Learning](https://mlsanity.com/paper/2211.00194/) (2022)
- [Image Data Augmentation Approaches: A Comprehensive Survey and Future directions](https://mlsanity.com/paper/2301.02830/) (2023)
- [Real Risks of Fake Data: Synthetic Data, Diversity-Washing and Consent Circumvention](https://mlsanity.com/paper/2405.01820/) (2024)
- [Dimensionless machine learning: Imposing exact units equivariance](https://mlsanity.com/paper/2204.00887/) (2022)
- [Fine-grained Recognition with Learnable Semantic Data Augmentation](https://mlsanity.com/paper/2309.00399/) (2023)
- [Practical Recommendations for Replay-based Continual Learning Methods](https://mlsanity.com/paper/2203.10317/) (2022)
- [Boomerang: Local sampling on image manifolds using diffusion models](https://mlsanity.com/paper/2210.12100/) (2022)
- [SaGess: Sampling Graph Denoising Diffusion Model for Scalable Graph Generation](https://mlsanity.com/paper/2306.16827/) (2023)
- [CAD2Render: A Modular Toolkit for GPU-accelerated Photorealistic Synthetic Data Generation for the Manufacturing Industry](https://mlsanity.com/paper/2211.14054/) (2022)
- [Recursive Learning Without Collapse: A Weighting-Based Stabilization Framework](https://mlsanity.com/paper/2502.18049/) (2025)
- [Beyond Known Reality: Exploiting Counterfactual Explanations for Medical Research](https://mlsanity.com/paper/2307.02131/) (2023)
- [Can Question Generation Debias Question Answering Models? A Case Study on Question-Context Lexical Overlap](https://mlsanity.com/paper/2109.11256/) (2021)
- [Solving the Class Imbalance Problem Using a Counterfactual Method for Data Augmentation](https://mlsanity.com/paper/2111.03516/) (2021)
- [Adversarially Robust Models may not Transfer Better: Sufficient Conditions for Domain Transferability from the View of Regularization](https://mlsanity.com/paper/2202.01832/) (2022)
- [EEG Synthetic Data Generation Using Probabilistic Diffusion Models](https://mlsanity.com/paper/2303.06068/) (2023)
- [Influence-guided Data Augmentation for Neural Tensor Completion](https://mlsanity.com/paper/2108.10248/) (2021)
- [Invariance encoding in sliced-Wasserstein space for image classification with limited training data](https://mlsanity.com/paper/2201.02980/) (2022)
- [Dream to Adapt: Meta Reinforcement Learning by Latent Context Imagination and MDP Imagination](https://mlsanity.com/paper/2311.06673/) (2023)
- [The Age of Correlated Features in Supervised Learning based Forecasting](https://mlsanity.com/paper/2103.00092/) (2021)
- [A Review on Edge Analytics: Issues, Challenges, Opportunities, Promises, Future Directions, and Applications](https://mlsanity.com/paper/2107.06835/) (2021)
- [Mask Conditional Synthetic Satellite Imagery](https://mlsanity.com/paper/2302.04305/) (2023)
- [Data Augmentation for Depression Detection Using Skeleton-Based Gait Information](https://mlsanity.com/paper/2201.01115/) (2022)
- [Generative Adversarial Networks for Image Augmentation in Agriculture: A Systematic Review](https://mlsanity.com/paper/2204.04707/) (2022)

## 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.