Sign in

Alleviation of Gradient Exploding in GANs: Fake Can Be Real

By Song Tao and Jia Wang
In order to alleviate the notorious mode collapse phenomenon in generative adversarial networks (GANs), we propose a novel training method of GANs in which certain fake samples are considered as real ones during the training process. This strategy can reduce the gradient value that generator receives in the region where... Show more
March 16, 2020
=
0
Loading PDF…
Loading full text...
Similar articles
Loading recommendations...
=
0
x1
Alleviation of Gradient Exploding in GANs: Fake Can Be Real
Click on play to start listening