Augmenting Image Classifiers Using Data Augmentation Generative Adversarial Networks

Effective training of neural networks requires a lot of data. In the low-data regime, parameters are underdetermined, and learnt networks generalise poorly. Data Augmentation alleviates this by using existing data more effectively. However standard data augmentation produces only limited plausible alternative data. Given there is potential to generate a much broader set of augmentations, we design and train a generative model to do data augmentation. The model, based on image conditional Generative Adversarial Networks, takes data from a source domain and learns to take any data item and augment it by generating other within-class data items. As this generative process does not depend on the classes themselves, it can be applied to novel unseen classes of data. We demonstrate that a Data Augmentation Generative Adversarial Network (DAGAN) augments classiers very well on Omniglot, EMNIST and VGG-Face.