Publication
ICML 2017
Conference paper

McGan: Mean and covariance feature matching GAN

Abstract

We introduce new families of Integral Probability Metrics (IPM) for training Generative Adversarial Networks (GAN). Our IPMs are based on matching statistics of distributions embedded in a finite dimensional feature space. Mean and co-variance feature matching IPMs allow for stable training of GANs, which we will call McGan. McGan minimizes a meaningful loss between distributions.

Date

06 Aug 2017

Publication

ICML 2017

Authors

Share