Stacked Generative Adversarial Networks

This repository contains code for the paper "Stacked Generative Adversarial Networks", CVPR 2017. Part of the code is modified from OpenAI's implementation of Improved GAN.

Architecture

Samples

Performance Comprison on CIFAR-10

Method	Inception Score
Infusion training	4.62 ± 0.06
GMAN (best variant)	5.34 ± 0.05
LR-GAN	6.11 ± 0.06
EGAN-Ent-VI	7.07 ± 0.10
Denoising feature matching	7.72 ± 0.13
DCGAN	6.58
SteinGAN	6.35
Improved GAN（best variant)	8.09 ± 0.07
AC-GAN	8.25 ± 0.07
SGAN (ours)	8.59 ± 0.12

Citations

If you use the code in this repository in your paper, please consider citing:

@inproceedings{huang2017sgan,
  title={Stacked Generative Adversarial Networks},
  author={Huang, Xun and Li, Yixuan and Poursaeed, Omid and Hopcroft, John and Belongie, Serge},
  booktitle={CVPR},
  year={2017}
}

Contact

If you have any questions about the code, feel free to email me (xh258@cornell.edu).