节点文献

Generative Adversarial Network with Separate Learning Rule for Image Generation

免费订阅

【作者】 印峰陈新雨邱杰康永亮

【Author】 YIN Feng;CHEN Xinyu;QIU Jie;KANG Yongliang;College of Automation and Electronic Information,Xiangtan University;National Engineering Laboratory of Robot Vision Perception and Control Technology;

【通讯作者】 印峰;

【机构】 College of Automation and Electronic Information Xiangtan UniversityNational Engineering Laboratory of Robot Vision Perception and Control Technology

【摘要】 Boundary equilibrium generative adversarial networks(BEGANs) are the improved version of generative adversarial networks(GANs). In this paper, an improved BEGAN with a skip-connection technique in the generator and the discriminator is proposed. Moreover, an alternative time-scale update rule is adopted to balance the learning rate of the generator and the discriminator. Finally, the performance of the proposed method is quantitatively evaluated by Fréchet inception distance(FID) and inception score(IS). The test results show that the performance of the proposed method is better than that of the original BEGAN.

【基金】 National Natural Science Foundation of China(Nos.61602398 and U19A2083);Science and Technology Department of Hunan Province,China(No.2019GK4007)
  • 【分类号】TP391.41;TP183
  • 【下载频次】3
节点文献中: 

本文链接的文献网络图示:

浏览历史:
下载历史: