An Improvement based on Wasserstein GAN for Alleviating Mode Collapsing | |
Yingying Chen1,2; Xinwen Hou1 | |
2020-07 | |
会议日期 | July 19, 2020 - July 24, 2020 |
会议地点 | Virtual, Glasgow, United kingdom |
DOI | 10.1109/IJCNN48605.2020.9207717 |
英文摘要 | In the past few years, Generative Adversarial Networks as a deep generative model has received more and more attention. Mode collapsing is one of the challenges in the study of Generative Adversarial Networks. In order to solve this problem, we deduce a new algorithm on the basis of Wasserstein GAN. We add a generated distribution entropy term to the objective function of generator net and maximize the entropy to increase the diversity of fake images. And then Stein Variational Gradient Descent algorithm is used for optimization. We named our method SW-GAN. In order to substantiate our theoretical analysis, we perform experiments on MNIST and CIFAR-10, and the results demonstrate superiority of our method. |
源文献作者 | Institute of Electrical and Electronics Engineers Inc., United States |
会议录出版者 | Institute of Electrical and Electronics Engineers Inc |
语种 | 英语 |
URL标识 | 查看原文 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/44934] |
专题 | 综合信息系统研究中心_脑机融合与认知评估 |
通讯作者 | Xinwen Hou |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, |
推荐引用方式 GB/T 7714 | Yingying Chen,Xinwen Hou. An Improvement based on Wasserstein GAN for Alleviating Mode Collapsing[C]. 见:. Virtual, Glasgow, United kingdom. July 19, 2020 - July 24, 2020. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论