Input limited Wasserstein GAN

Feidao Cao; Huaici Zhao; Pengfei Liu; Peixuan Li

doi:10.1117/12.2552451

31 January 2020 Input limited Wasserstein GAN

Feidao Cao, Huaici Zhao, Pengfei Liu, Peixuan Li

Proceedings Volume 11427, Second Target Recognition and Artificial Intelligence Summit Forum; 114272N (2020) https://doi.org/10.1117/12.2552451
Event: Second Target Recognition and Artificial Intelligence Summit Forum, 2019, Changchun, China

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.

Citation Download Citation

Feidao Cao, Huaici Zhao, Pengfei Liu, and Peixuan Li "Input limited Wasserstein GAN", Proc. SPIE 11427, Second Target Recognition and Artificial Intelligence Summit Forum, 114272N (31 January 2020); https://doi.org/10.1117/12.2552451

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available