Mila > Publication > The relativistic discriminator: a key element missing from standard GAN

The relativistic discriminator: a key element missing from standard GAN

Sep 2018

The relativistic discriminator: a key element missing from standard GAN

Sep 2018

In standard generative adversarial network (SGAN), the discriminator estimates the probability that the input data is real. The generator is trained to increase the probability that fake data is real. We argue that it should also simultaneously decrease the probability that real data is real because 1) this would account for a priori knowledge that half of the data in the mini-batch is fake, 2) this would be observed with divergence minimization, and 3) in optimal settings, SGAN would be equivalent to integral probability metric (IPM) GANs.

Reference

https://openreview.net/forum?id=S1erHoR5t7

Linked Profiles