BEGAN: Boundary Equilibrium Generative Adversarial Networks

31 Mar 2017David BerthelotThomas SchummLuke Metz

We propose a new equilibrium enforcing method paired with a loss derived from the Wasserstein distance for training auto-encoder based Generative Adversarial Networks. This method balances the generator and discriminator during training... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Image Generation CIFAR-10 BEGAN Inception score 5.62 # 12