arxivst stuff from arxiv that you should probably bookmark

BEGAN: Boundary Equilibrium Generative Adversarial Networks

Abstract · Mar 31, 2017 00:13 ·

cs-lg stat-ml

Arxiv Abstract

  • David Berthelot
  • Tom 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.

Read the paper (pdf) »