Share Email Print
cover

Proceedings Paper

Input limited Wasserstein GAN
Author(s): Feidao Cao; Huaici Zhao; Pengfei Liu; Peixuan Li
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Generative adversarial networks (GANs) has proven hugely successful, but suffer from train instability. The recently proposed Wasserstein GAN (WGAN) has largely overcome the problem, but can still fail to converge in some case or be to complex. It has been found that the use of weight clipping in WGAN to enforce a Lipschitz constraint on the critic, is the cause of the failure. We modify network architecture: use domain constraint layer instead of the use of weight clipping in WGAN. Experimental results show that our proposed method generates higher quality images than WGAN with weight clipping. And architecture is sample. Beside the network is more stable and easier to train.

Paper Details

Date Published: 31 January 2020
PDF: 5 pages
Proc. SPIE 11427, Second Target Recognition and Artificial Intelligence Summit Forum, 114272N (31 January 2020);
Show Author Affiliations
Feidao Cao, Shenyang Institute of Automation/Institutes for Robotics and Intelligent Manufacturing (China)
Univ. of Chinese Academy of Sciences (China)
Key Labs. of Opto-Electronic Information Processing/Image Understanding and Computer Vision (China)
Huaici Zhao, Shenyang Institute of Automation/Institutes for Robotics and Intelligent Manufacturing (China)
Key Labs. of Opto-Electronic Information Processing/Image Understanding and Computer Vision (China)
Pengfei Liu, Shenyang Institute of Automation/Institutes for Robotics and Intelligent Manufacturing (China)
Univ. of Chinese Academy of Sciences (China)
Key Labs. of Opto-Electronic Information Processing/Image Understanding and Computer Vision (China)
Peixuan Li, Shenyang Institute of Automation/Institutes for Robotics and Intelligent Manufacturing (China)
Univ. of Chinese Academy of Sciences (China)
Key Labs. of Opto-Electronic Information Processing/Image Understanding and Computer Vision (China)


Published in SPIE Proceedings Vol. 11427:
Second Target Recognition and Artificial Intelligence Summit Forum
Tianran Wang; Tianyou Chai; Huitao Fan; Qifeng Yu, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray