论文标题
真实与否，这是一个问题
Real or Not Real, that is the Question
论文作者
论文摘要
尽管生成对抗网络（GAN）在各种主题中已被广泛采用，但在本文中，我们通过将现实性视为可以从多个角度估算的随机变量来将标准GAN推广到新的视角。在这个被称为Realnessgan的广义框架中，歧视者将分布作为现实度的度量。尽管Realnessgan与标准GAN具有类似的理论保证，但它提供了更多关于对抗性学习的见解。与多个基线相比，Realnessgan为发电机提供了更强大的指导，从而在合成数据集和现实世界数据集方面取得了改进。此外，它使基本的DCGAN体系结构能够在从头开始训练时以1024*1024分辨率生成逼真的图像。
While generative adversarial networks (GAN) have been widely adopted in various topics, in this paper we generalize the standard GAN to a new perspective by treating realness as a random variable that can be estimated from multiple angles. In this generalized framework, referred to as RealnessGAN, the discriminator outputs a distribution as the measure of realness. While RealnessGAN shares similar theoretical guarantees with the standard GAN, it provides more insights on adversarial learning. Compared to multiple baselines, RealnessGAN provides stronger guidance for the generator, achieving improvements on both synthetic and real-world datasets. Moreover, it enables the basic DCGAN architecture to generate realistic images at 1024*1024 resolution when trained from scratch.
