SIA OpenIR  > 光电信息技术研究室
Input limited Wasserstein GAN
Cao FD(曹飞道)1,2,3,4,5; Zhao HC(赵怀慈)1,2,4,5; Liu PF(刘鹏飞)1,2,3,4,5; Li PX(李培玄)1,2,3,4,5
Department光电信息技术研究室
Conference Name2nd Target Recognition and Artificial Intelligence Summit Forum 2019
Conference DateAugust 28-30, 2019
Conference PlaceShenyang, China
Author of SourceChinese Society for Optical Engineering
Source PublicationSecond Target Recognition and Artificial Intelligence Summit Forum
PublisherSPIE
Publication PlaceBellingham, USA
2019
Pages1-5
Indexed ByEI
EI Accession number20201108282800
Contribution Rank1
ISSN0277-786X
ISBN978-1-5106-3631-6
KeywordWGAN stability domain constrain layer
AbstractGenerative 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.
Language英语
Document Type会议论文
Identifierhttp://ir.sia.cn/handle/173321/26416
Collection光电信息技术研究室
Corresponding AuthorZhao HC(赵怀慈)
Affiliation1.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, Liaoning 110016, China
2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, Liaoning 110016, China
3.University of Chinese Academy of Sciences, Beijing 100049, China
4.Key Laboratory of Opto-Electronic Information Processing, CAS, Shenyang, Liaoning 110016, China
5.Key Lab of Image Understanding and Computer Vision, Liaoning Province, Shenyang 110016, China
Recommended Citation
GB/T 7714
Cao FD,Zhao HC,Liu PF,et al. Input limited Wasserstein GAN[C]//Chinese Society for Optical Engineering. Bellingham, USA:SPIE,2019:1-5.
Files in This Item: Download All
File Name/Size DocType Version Access License
Input limited Wasser(913KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Cao FD(曹飞道)]'s Articles
[Zhao HC(赵怀慈)]'s Articles
[Liu PF(刘鹏飞)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Cao FD(曹飞道)]'s Articles
[Zhao HC(赵怀慈)]'s Articles
[Liu PF(刘鹏飞)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Cao FD(曹飞道)]'s Articles
[Zhao HC(赵怀慈)]'s Articles
[Liu PF(刘鹏飞)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Input limited Wasserstein GAN.pdf
Format: Adobe PDF
This file does not support browsing at this time
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.