papers AI Learner
The Github is limit! Click to go to the new site.

Fisher GAN

2017-11-03
Youssef Mroueh, Tom Sercu

Abstract

Generative Adversarial Networks (GANs) are powerful models for learning complex distributions. Stable training of GANs has been addressed in many recent works which explore different metrics between distributions. In this paper we introduce Fisher GAN which fits within the Integral Probability Metrics (IPM) framework for training GANs. Fisher GAN defines a critic with a data dependent constraint on its second order moments. We show in this paper that Fisher GAN allows for stable and time efficient training that does not compromise the capacity of the critic, and does not need data independent constraints such as weight clipping. We analyze our Fisher IPM theoretically and provide an algorithm based on Augmented Lagrangian for Fisher GAN. We validate our claims on both image sample generation and semi-supervised classification using Fisher GAN.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1705.09675

PDF

https://arxiv.org/pdf/1705.09675


Similar Posts

Comments