Timezone: »

McGan: Mean and Covariance Feature Matching GAN
Youssef Mroueh · Tom Sercu · Vaibhava Goel

Mon Aug 07 01:30 AM -- 05:00 AM (PDT) @ Gallery #50

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.

Author Information

Youssef Mroueh (IBM T.J Watson Research Center)
Tom Sercu (IBM Research)
Vaibhava Goel (IBM)

Related Events (a corresponding poster, oral, or spotlight)