McGan: Mean and Covariance Feature Matching GAN
This addresses training instability for researchers and practitioners using GANs, but appears incremental as it builds on existing IPM-based methods.
The paper tackles the problem of training instability in Generative Adversarial Networks (GANs) by introducing McGan, which uses mean and covariance feature matching Integral Probability Metrics (IPMs) to minimize a meaningful loss between distributions, resulting in stable training.
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.