GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium

NeurIPS 2017 Martin HeuselHubert RamsauerThomas UnterthinerBernhard NesslerSepp Hochreiter

Generative Adversarial Networks (GANs) excel at creating realistic images with complex models for which maximum likelihood is infeasible. However, the convergence of GAN training has still not been proved... (read more)

PDF Abstract

Evaluation results from the paper

#3 best model for Image Generation on CIFAR-10 (FID metric)

     Get a GitHub badge
Task Dataset Model Metric name Metric value Global rank Compare
Image Generation CIFAR-10 WGAN-GP + TT Update Rule FID 24.8 # 3
Image Generation LSUN Bedroom 256 x 256 WGAN-GP + TT Update Rule FID 9.5 # 4