Input limited Wasserstein GAN
文献类型：会议论文
| 作者 | Cao FD(曹飞道)1,2,3,4,5 ; Zhao HC(赵怀慈)1,2,3,4; Liu PF(刘鹏飞)1,2,3,4,5; Li PX(李培玄)1,2,3,4,5
|
| 出版日期 | 2019 |
| 会议日期 | August 28-30, 2019 |
| 会议地点 | Shenyang, China |
| 关键词 | WGAN stability domain constrain layer |
| 页码 | 1-5 |
| 英文摘要 | 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. |
| 源文献作者 | Chinese Society for Optical Engineering |
| 产权排序 | 1 |
| 会议录 | Second Target Recognition and Artificial Intelligence Summit Forum
 |
| 会议录出版者 | SPIE |
| 会议录出版地 | Bellingham, USA |
| 语种 | 英语 |
| ISSN号 | 0277-786X |
| ISBN号 | 978-1-5106-3631-6 |
| WOS记录号 | WOS:000546230500092 |
| 源URL | [http://ir.sia.cn/handle/173321/26416]  |
| 专题 | 沈阳自动化研究所_光电信息技术研究室 |
| 通讯作者 | Zhao HC(赵怀慈) |
| 作者单位 | 1.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, Liaoning 110016, China 2.Key Laboratory of Opto-Electronic Information Processing, CAS, Shenyang, Liaoning 110016, China 3.Key Lab of Image Understanding and Computer Vision, Liaoning Province, Shenyang 110016, China 4.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, Liaoning 110016, China 5.University of Chinese Academy of Sciences, Beijing 100049, China |
| 推荐引用方式 GB/T 7714 | Cao FD,Zhao HC,Liu PF,et al. Input limited Wasserstein GAN[C]. 见:. Shenyang, China. August 28-30, 2019. |
入库方式： OAI收割
来源：沈阳自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。