Generative adversarial network: Difference between revisions
No edit summary |
|||
| Line 13: | Line 13: | ||
==Variations== | ==Variations== | ||
===Conditional GAN=== | |||
[https://arxiv.org/abs/1411.1784 Paper]<br> | |||
Feed data y to both generator and discriminator | |||
===Wasserstein GAN=== | ===Wasserstein GAN=== | ||
[https://arxiv.org/pdf/1704.00028.pdf Paper]<br> | [https://arxiv.org/pdf/1704.00028.pdf Paper]<br> | ||
Revision as of 14:16, 7 January 2020
GANs are generative adversarial networks. They were developed by Ian Goodfellow.
Goal: Learn to generate examples from the same distribution as your training set.
Basis Structure
GANs consist of a generator and a discriminator.
For iteration i
For iteration j
Update Discriminator
Update Generator
Variations
Conditional GAN
Paper
Feed data y to both generator and discriminator
Wasserstein GAN
Paper
Medium post
This new WGAN-GP loss function improves the stability of training.
Normally, the discriminator is trained with a cross-entropy with sigmoid loss function.
The WGAN proposes using Wasserstein distance which is implemented by removing the cross-entropy+sigmoid
and clipping (clamp) the weights on the discriminator to a range \(\displaystyle [-c, c]\).
However, weight clipping leads to other issues which limit the critic.
Instead of clipping, WGAN-GP proposes gradient penalty to enforce 1-Lipschitz .
Applications
CycleGan
InfoGAN
SinGAN
Paper
Website
Github Official PyTorch Implementation
SinGAN: Learning a Generative Model from a Single Natural Image
MoCoGAN
Paper
MoCoGAN: Decomposing Motion and Content for Video Generation