Improving the Speed and Quality of GAN by Adversarial Training

Jiachen Zhong
Jiachen Zhong
Xuanqing Liu
Xuanqing Liu
Cited by: 0|Bibtex|Views13|Links

Abstract:

Generative adversarial networks (GAN) have shown remarkable results in image generation tasks. High fidelity class-conditional GAN methods often rely on stabilization techniques by constraining the global Lipschitz continuity. Such regularization leads to less expressive models and slower convergence speed; other techniques, such as the...More

Code:

Data:

Your rating :
0

 

Tags
Comments