Generative Adversarial Nets (GANs) represent an important milestone for effective generative models, which has inspired numerous variants seemingly different from each other. One of the main contributions of this paper is to reveal a unified geometric structure in GAN and its variants. Specifically, we show that the adversarial generative model training can be decomposed into three geometric steps: separating hyperplane search, discriminator parameter update away from the separating hyperplane, and the generator update along the normal vector direction of the separating hyperplane. This geometric intuition reveals the limitations of the existing approaches and leads us to propose a new formulation called geometric GAN using SVM separating hyperplane that maximizes the margin. Our theoretical analysis shows that the geometric GAN converges to a Nash equilibrium between the discriminator and generator. In addition, extensive numerical results show that the superior performance of geometric GAN.
Models | Dataset | SWD | MS-SSIM | FID | Config | Download |
---|---|---|---|---|---|---|
GGAN 64x64 | CelebA-Cropped | 11.18, 12.21, 39.16/20.85 | 0.3318 | 20.1797 | config | model | log |
GGAN 128x128 | CelebA-Cropped | 9.81, 11.29, 19.22, 47.79/22.03 | 0.3149 | 18.7647 | config | model | log |
GGAN 64x64 | LSUN-Bedroom | 9.1, 6.2, 12.27/9.19 | 0.0649 | 85.6629 | config | model | log |
Note: In the original implementation of GGAN, they set G_iters
to 10. However our framework does not support G_iters
currently, so we dropped the settings in the original implementation and conducted several experiments with our own settings. We have shown above the experiment results with the lowest fid
score.
Original settings and our settings:
Models | Dataset | Architecture | optimizer | lr_G | lr_D | G_iters | D_iters |
---|---|---|---|---|---|---|---|
GGAN(origin) 64x64 | CelebA-Cropped | dcgan-archi | RMSprop | 0.0002 | 0.0002 | 10 | 1 |
GGAN(ours) 64x64 | CelebA-Cropped | dcgan-archi | Adam | 0.001 | 0.001 | 1 | 1 |
GGAN(origin) 64x64 | LSUN-Bedroom | dcgan-archi | RMSprop | 0.0002 | 0.0002 | 10 | 1 |
GGAN(ours) 64x64 | LSUN-Bedroom | lsgan-archi | Adam | 0.0001 | 0.0001 | 1 | 1 |
@article{lim2017geometric,
title={Geometric gan},
author={Lim, Jae Hyun and Ye, Jong Chul},
journal={arXiv preprint arXiv:1705.02894},
year={2017},
url={https://arxiv.org/abs/1705.02894},
}
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。