Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

Jun-Yan Zhu, Taesung Park, Phillip Isola, Alexei A. Efros

Abstract

任务：Image-to-image translation(learn the mapping between an input image and an output image using a training set of aligned image pairs)
困难：paired training data will not be available
解决方案：learning to translate an image from a source domain $X$ to a target domain $Y$ in the absence of paired examples
具体方法：learn a mapping $G:X\to Y$ such that the distribution of images from $G(x)$ is indistinguishable from the distribution $Y$ using an adversarial loss. 但是直接这么做约束太弱了，于是加了另外一个约束$F:Y\to X$使得$F$是$G$的反函数，即$F(G(x)) \approx G(F(x)) \approx x$。这就是CycleGAN的基本思想（后来ICLR2018的一篇用GAN在隐空间生成对抗样本的工作和这个很像）

Introduction

开头两段很有文采~
为了避免image translation中搜集标记数据集的困难，可以直接进行集合层面上而不是元素层面上的匹配，即domain mapping。进行domain mapping，就是要找到一个 G