StyleMix: Separating Content and Style for Enhanced Data Augmentation

In spite of the great success of deep neural networks for many challenging classification tasks, the learned networks are vulnerable to overfitting and adversarial attacks. Recently, mixup based augmentation methods have been actively studied as one practical remedy for these drawbacks. However, these approaches do not distinguish between the content and style features of the image, but mix or cut-andpaste the images. We propose StyleMix and StyleCutMix as the first mixup method that separately manipulates the content and style information of input image pairs. By carefully mixing up the content and style of images, we can create more abundant and robust samples, which eventually enhance the generalization of model training. We also develop an automatic scheme to decide the degree of style mixing according to the pair's class distance, to prevent messy mixed images from too differently styled pairs. Our experiments on CIFAR-10, CIFAR-100 and ImageNet datasets show that StyleMix achieves better or comparable performance to state of the art mixup methods and learns more robust classifiers to adversarial attacks.