Aman Kumar, Khushboo Anand, Shubham Mandloi, Ashutosh Mishra, Avinash Thakur...
TL;DR提出了一种利用可微的修剪方法通过超网络压缩 GAN 的方法,实现可控压缩训练,并在多个基准数据集上取得了优异的性能。
Abstract
generative adversarial networks (GANs) have proven to exhibit remarkable
performance and are widely used across many generative computer vision
applications. However, the unprecedented demand for the deployment of GANs on
resource-constrained edge devices still poses a challenge due to