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.
@article{arxiv.1609.08764,
title = {Understanding data augmentation for classification: when to warp?},
author = {Sebastien C. Wong and Adam Gatt and Victor Stamatescu and Mark D. McDonnell},
journal= {arXiv preprint arXiv:1609.08764},
year = {2016}
}