Adversarial Feature Learning

BiGAN：使用双向GAN进行对抗特征学习.

Autoencoding beyond pixels using a learned similarity metric

VAE-GAN：结合VAE和GAN.

Energy-based Generative Adversarial Network

EBGAN：基于能量的生成对抗网络.

Least Squares Generative Adversarial Networks

LSGAN：使用均方误差构造目标函数.

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

CycleGAN：使用循环一致损失实现无配对数据的图像转换.

Wasserstein GANs Work Because They Fail (to Approximate the Wasserstein Distance)

WGAN的表现与Wasserstein距离的近似程度没有必然联系.