Conference Proceedings

Improving MMD-GaN training with repulsive loss function

W Wang, Y Sun, S Halgamuge

Proceedings of the 7th International Conference on Learning Representations, ICLR 2019 | dblp | Published : 2019

Abstract

Generative adversarial nets (GANs) are widely used to learn the data sampling process and their performance may heavily depend on the loss functions, given a limited computational budget. This study revisits MMD-GAN that uses the maximum mean discrepancy (MMD) as the loss function for GAN and makes two contributions. First, we argue that the existing MMD loss function may discourage the learning of fine details in data as it attempts to contract the discriminator outputs of real data. To address this issue, we propose a repulsive loss function to actively learn the difference among the real data by simply rearranging the terms in MMD. Second, inspired by the hinge loss, we propose a bounded ..

View full abstract

University of Melbourne Researchers