Generative adversarial network: Difference between revisions

From David's Wiki
No edit summary
Line 37: Line 37:
[https://arxiv.org/abs/1707.04993 Paper]<br>
[https://arxiv.org/abs/1707.04993 Paper]<br>
MoCoGAN: Decomposing Motion and Content for Video Generation<br>
MoCoGAN: Decomposing Motion and Content for Video Generation<br>
==Resources==
* [https://github.com/soumith/ganhacks Tricks for Training GANs]

Revision as of 13:18, 19 December 2019

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

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

Resources