BEGAN: Boundary Equilibrium Generative Adversarial Networks
David Berthelot
and
Thomas Schumm
and
Luke Metz
arXiv e-Print archive - 2017 via Local arXiv
Keywords:
cs.LG, stat.ML
First published: 2017/03/31 (7 years ago) Abstract: 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.
