Generative adversarial network: Difference between revisions
| (5 intermediate revisions by the same user not shown) | |||
| Line 2: | Line 2: | ||
Goal: Learn to generate examples from the same distribution as your training set. | Goal: Learn to generate examples from the same distribution as your training set. | ||
== | ==Structure== | ||
GANs consist of a generator and a discriminator. | GANs consist of a generator and a discriminator, both of which are usually CNNs. | ||
<pre> | <pre> | ||
| Line 11: | Line 11: | ||
Update Generator | Update Generator | ||
</pre> | </pre> | ||
===Generator=== | |||
Two popular types of CNNs used in GANs are Resnets and UNets.<br> | |||
In both cases, we have convolutional blocks which consist of a conv2d layer, a batch norm, and an activation (typically Relu or leakyrelu). | |||
===Discriminator=== | |||
A popular discriminator is the PatchGAN discriminator.<br> | |||
These are typically several convolutional blocks stacked together. | |||
Each convolutional layer in the conv block typically has a kernel size of (3x3) or (4x4) and a stride of 1-2. | |||
==Variations== | ==Variations== | ||
| Line 26: | Line 36: | ||
However, weight clipping leads to other issues which limit the critic.<br> | However, weight clipping leads to other issues which limit the critic.<br> | ||
Instead of clipping, WGAN-GP proposes gradient penalty to enforce 1-Lipschitz . | Instead of clipping, WGAN-GP proposes gradient penalty to enforce 1-Lipschitz . | ||
===Progressive Growing of GANs (ProGAN)=== | |||
[https://arxiv.org/abs/1710.10196 Paper]<br> | |||
Progressively add layers to the generator and the discriminator of the GAN.<br> | |||
At the beginning, the generator makes a 4x4 image and the discriminator takes input the 4x4 image. | |||
Then, another layer is faded in the generator and the discriminator for and 8x8 image,... | |||
===Stacked Generative Adversarial Networks=== | |||
[https://arxiv.org/abs/1612.04357 Paper]<br> | |||
==Applications== | ==Applications== | ||
| Line 54: | Line 73: | ||
** Colorize with GAN. Only transmit luminance (Y of YUV) | ** Colorize with GAN. Only transmit luminance (Y of YUV) | ||
** The paper claims 72% BDBR reduction compared to HM 16.0. | ** The paper claims 72% BDBR reduction compared to HM 16.0. | ||
===Object Segmentation=== | |||
* [https://arxiv.org/abs/1905.11369 Object Discovery with a Copy-Pasting GAN] | |||
===StyleGAN=== | |||
{{ main | StyleGAN }} | |||
==Important Papers== | ==Important Papers== | ||
| Line 59: | Line 84: | ||
===Latent Space Exploration=== | ===Latent Space Exploration=== | ||
* [https://arxiv.org/abs/1907.10786 Interpreting the Latent Space of GANs for Semantic Face Editing] | |||
* [https://arxiv.org/abs/1907.07171 On the "steerability" of generative adversarial networks] | * [https://arxiv.org/abs/1907.07171 On the "steerability" of generative adversarial networks] | ||