BEGAN: Boundary Equilibrium Generative Adversarial Networks

31 Mar 2017  ·  David 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. We also derive a way of controlling the trade-off between image diversity and visual quality. We focus on the image generation task, setting a new milestone in visual quality, even at higher resolutions. This is achieved while using a relatively simple model architecture and a standard training procedure.

PDF Abstract

Datasets


Results from the Paper


Ranked #68 on Image Generation on CIFAR-10 (Inception score metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Generation CIFAR-10 BEGAN Inception score 5.62 # 68

Methods


No methods listed for this paper. Add relevant methods here