Hamid Eghbal-zadeh, Werner Zellinger, Gerhard Widmer
TL;DR本文提出了一种新型 GAN 变体 Mixutre Density GAN,通过在判别器嵌入空间中形成聚类来打破生成器的模式崩塌问题,从而发现不同的数据模式,并在生成高质量图像方面表现出色。
Abstract
generative adversarial networks have surprising ability for generating sharp
and realistic images, though they are known to suffer from the so-called mode
collapse problem. In this paper, we propose a new GAN variant called Mixture
Density GAN that while being capable of generating hig