TL;DR通过使用Inverse Generator Model 作为编码器和预先训练好的Generator作为解码器的AutoEncoder网络来训练Inverse Model，本文提出了一种新方法来训练GAN生成器的Inverse Model，在图像搜索中比传统方法表现更好。
Abstract
Generative Adversarial Net has shown its great ability in generating samples. The inverse mapping of generator also contains a great value. Some works have been developed to construct the inverse function of