Abstract Random data augmentation is a critical technique to avoid overfifitting in training deep neural network models. However, data augmentation and network training are usually treated as two isolated processes, limiting the effectiveness of network training. Why not jointly optimize the two? We propose adversarial data augmentation to address this limitation. The main idea is to design an augmentation network (generator) that competes against a target network (discriminator) by generating “hard” augmentation operations online. The augmentation network explores the weaknesses of the target network, while the latter learns from “hard” augmentations to achieve better performance. We also design a reward/penalty strategy for effective joint training. We demonstrate our approach on the problem of human pose estimation and carry out a comprehensive experimental analysis, showing that our method can signifificantly improve state-of-the-art models without additional data efforts