On Catastrophic Forgetting and Mode Collapse in Generative Adversarial Networks

In this paper, we show that Generative Adversarial Networks (GANs) suffer from catastrophic forgetting even when they are trained to approximate a single target distribution. We show that GAN training is a continual learning problem in which the sequence of changing model distributions is the sequence of tasks to the discriminator... (read more)

Results in Papers With Code
(↓ scroll down to see all results)