LOGAN: Latent Optimisation for Generative Adversarial Networks

Wu Yan
Wu Yan
Lillicrap Timothy
Lillicrap Timothy
Cited by: 15|Bibtex|Views105
Other Links: arxiv.org

Abstract:

Training generative adversarial networks requires balancing of delicate adversarial dynamics. Even with careful tuning, training may diverge or end up in a bad equilibrium with dropped modes. In this work, we introduce a new form of latent optimisation inspired by the CS-GAN and show that it improves adversarial dynamics by enhancing in...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments