Towards Efficient and Unbiased Implementation of Lipschitz Continuity in GANs
arXiv:1904.01184
Abstract
Lipschitz continuity recently becomes popular in generative adversarial networks (GANs). It was observed that the Lipschitz regularized discriminator leads to improved training stability and sample quality. The mainstream implementations of Lipschitz continuity include gradient penalty and spectral normalization. In this paper, we demonstrate that gradient penalty introduces undesired bias, while spectral normalization might be over restrictive. We accordingly propose a new method which is efficient and unbiased. Our experiments verify our analysis and show that the proposed method is able to achieve successful training in various situations where gradient penalty and spectral normalization fail.
Submitted to IJCAI 2019
References in corpus (7)
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- On the Convergence of Adam and Beyond
- On Convergence and Stability of GANs
- Spectral Norm Regularization for Improving the Generalizability of Deep Learning
- On the regularization of Wasserstein GANs
- Lipschitz Generative Adversarial Nets
- AdaShift: Decorrelation and Convergence of Adaptive Learning Rate Methods