Game Theory Meets Data Augmentation

Data augmentation is a critical component in building modern deep-learning systems. In this article, we propose MFG Augment, a novel data augmentation method based on the mean-field game (MFG) theory that can synthesize a sequence of data between every two images or features. The central idea is to consider every image as a distribution over its pixel or feature space. Using MFG theory, we can generate a time-continuous “path” from one distribution to another so that the points along the “path” are augmented images or features. Empirically, the experiment results on MNIST, CIFAR-10, and ImageNet demonstrate that the proposed technology has better generalization ability and higher classification accuracy as compared to several benchmark methods. More importantly, our MFG Augment improves the test accuracy significantly when the dataset size is small. MFG Augment consistently shows better affinity and diversity scores, two important empirical metrics for evaluating the generalization of data augmentation techniques.