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 X to a target domain
in the absence of paired examples
具体方法:learn a mapping G:X→Y G : X → Y such that the distribution of images from G(x) G ( x ) is indistinguishable from the distribution Y 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
使得 F F 是
的反函数,即 F(G(x))≈G(F(x))≈x F ( G ( x ) ) ≈ G ( F ( x ) ) ≈ 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