Mixing Up Real Samples and Adversarial Samples for Semi-Supervised Learning

Yun Ma, Xudong Mao, Yangbin Chen, Qing Li

Abstract: Consistency regularization methods have shown great success in semi-supervised learning tasks. Most existing methods focus on either the local neighborhood or in-between neighborhood of training samples to enforce the consistency constraint. In this paper, we propose a novel generalized framework called Adversarial Mixup (AdvMixup), which unifies the local and in-between neighborhood approaches by defining a virtual data distribution along the paths between the training samples and adversarial samples. Experimental results on both synthetic data and benchmark datasets exhibit the benefits of AdvMixup on semi-supervised learning.