Gradient penalty from a maximum margin perspective

Code

• github.com/AlexiaJM/MaximumMarginGANs
  OfficialIn papertf★ 0
• github.com/lucidrains/stylegan2-pytorch
  pytorch★ 0

Abstract

A popular heuristic for improved performance in Generative adversarial networks (GANs) is to use some form of gradient penalty on the discriminator. This gradient penalty was originally motivated by a Wasserstein distance formulation. However, the use of gradient penalty in other GAN formulations is not well motivated. We present a unifying framework of expected margin maximization and show that a wide range of gradient-penalized GANs (e.g., Wasserstein, Standard, Least-Squares, and Hinge GANs) can be derived from this framework. Our results imply that employing gradient penalties induces a large-margin classifier (thus, a large-margin discriminator in GANs). We describe how expected margin maximization helps reduce vanishing gradients at fake (generated) samples, a known problem in GANs. From this framework, we derive a new L^ gradient norm penalty with Hinge loss which generally produces equally good (or better) generated output in GANs than L^2-norm penalties (based on the Fr\'echet Inception Distance).

Tasks

Benchmark Results

Reproductions