most citedMAGAN: Margin Adaptation for Generative Adversarial Networks

54 citations · 54 across the 1 of their papers we have counts for

collaborators

1 paper

cs.LG2017★ 54 cited

MAGAN: Margin Adaptation for Generative Adversarial Networks

Ruohan Wang, Antoine Cully, Hyung Jin Chang +1

We propose the Margin Adaptation for Generative Adversarial Networks (MAGANs) algorithm, a novel training procedure for GANs to improve stability and performance by using an adapti…