BEGAN: Boundary Equilibrium Generative Adversarial Networks

31 Mar 2017David Berthelot • Thomas Schumm • Luke 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. Additionally, it provides a new approximate convergence measure, fast and stable training and high visual quality.

Full paper


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