McGan: Mean and Covariance Feature Matching GAN
Youssef Mroueh · Tom Sercu · Vaibhava Goel
2017 Poster
[
PDF]
[
Summary/Notes]
Summary/Notes]
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 covariance feature matching IPMs allow for stable training of GANs, which we will call McGan. McGan minimizes a meaningful loss between distributions.
Chat is not available.
Successful Page Load