In a ground-breaking paper The relativistic discriminator: a key element missing from standard GAN by Alexia Jolicoeur-Martineau, it is argued that standard GAN, as described in Ian Goodfellow's first paper, is missing a fundamental property: training the generator should not only increase the probability that fake data is real, but also decrease the probability that real data is real.
Relativistic GANs are not completely new, as the Wasserstein GAN, the Wasserstein GAP with Gradient Penalty and the Least- Squares GAN already have a relativistic discriminator. These approaches are classified asThis possibly explains why these approaches are more standard GANs. Fortunately, the standard GANs can also be modified to become ...
