TL;DR本文提出了一种名为双判别器生成对抗网络(D2GAN)的生成对抗网络算法,该算法使用 KL 散度和反 KL 散度,避免了多峰性分布的崩塌问题,并在广泛的实验中证明了与最新 GAN 算法相比的竞争和卓越性能。
Abstract
We propose in this paper a novel approach to tackle the problem of mode
collapse encountered in generative adversarial network (GAN). Our idea is
intuitive but proven to be very effective, especially in addressing some key
limitations of GAN. In essence, it combines the Kullback-Leible