Learning Efficient GANs via Differentiable Masks and co-Attention Distillation

被引用0|浏览32

摘要

Generative Adversarial Networks (GANs) have been widely-used in image translation, but their high computational and storage costs impede the deployment on mobile devices. Prevalent methods for CNN compression cannot be directly applied to GANs due to the complicated generator architecture and the unstable adversarial training. To solve ...更多

代码

数据

下载 PDF 全文
引用
您的评分 :
0

 

标签
评论