Virtual Adversarial Lipschitz Regularization

by   Dávid Terjék, et al.

Generative adversarial networks (GANs) are one of the most popular approaches when it comes to training generative models, among which variants of Wasserstein GANs are considered superior to the standard GAN formulation in terms of learning stability and sample quality. However, Wasserstein GANs require the critic to be K-Lipschitz, which is often enforced implicitly by penalizing the norm of its gradient, or by globally restricting its Lipschitz constant via weight normalization techniques. Training with a regularization term penalizing the violation of the Lipschitz constraint explicitly, instead of through the norm of the gradient, was found to be practically infeasible in most situations. With a novel generalization of Virtual Adversarial Training, called Virtual Adversarial Lipschitz Regularization, we show that using an explicit Lipschitz penalty is indeed viable and leads to state-of-the-art performance in terms of Inception Score and Fréchet Inception Distance when applied to Wasserstein GANs trained on CIFAR-10.


On the regularization of Wasserstein GANs

Since their invention, generative adversarial networks (GANs) have becom...

Orthogonal Wasserstein GANs

Wasserstein-GANs have been introduced to address the deficiencies of gen...

Improved Training of Wasserstein GANs

Generative Adversarial Networks (GANs) are powerful generative models, b...

Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect

Despite being impactful on a variety of problems and applications, the g...

HRVGAN: High Resolution Video Generation using Spatio-Temporal GAN

In this paper, we present a novel network for high resolution video gene...

Banach Wasserstein GAN

Wasserstein Generative Adversarial Networks (WGANs) can be used to gener...

Improving the Speed and Quality of GAN by Adversarial Training

Generative adversarial networks (GAN) have shown remarkable results in i...

Please sign up or login with your details

Forgot password? Click here to reset