2 votes

What is the reason for mode collapse in GAN as opposed to WGAN?

I don't have a definite answer, but only a suspicion/idea: Looking at Figure 1 from the WGAN paper, we clear see that the JS divergence on the right is not continuous at $0$, hence not differentiable ...
Anonymous5638's user avatar
2 votes

How to calculate the gradient penalty proposed in "Improved Training of Wasserstein GANs"?

First of all, the discriminator in WGAN does not give a value in the range $[0,1]$. Compared to the traditional discriminator, it has a linear activation in the output layer. Therefore, the authors ...
Aray Karjauv's user avatar
1 vote

What to do with a GAN that trained well but got worse over time?

This is from my own experience with (Vanilla) GANs, so it might not translate exactly to your application, but maybe it gives some orientation. your learning rate seems quite high. I've quite ...
Mafu's user avatar
  • 144
1 vote
Accepted

Aren't scores in the Wasserstein GAN probabilities?

Figure 3 in the original WGAN paper is actually quite helpful to understand the difference between the score in WGAN and the probability in GAN (see screenshot below). The blue distribution are real ...
Mafu's user avatar
  • 144
1 vote

Do WGAN gradients require multi-variable calculus?

A function can be optimized, even if it has two inputs! First, note that the problem in question already occurs with traditional GANs as well. It might be easier to understand what is going on if you ...
Robin van Hoorn's user avatar
1 vote

Is Relativistic GAN better than WGAN-GP?

There is no one-size-fits-all answer to this question, as the two Generative Adversarial Network (GAN) models – Relativistic GAN and WGAN-GP – each have their own advantages and disadvantages. However,...
Faizy's user avatar
  • 1,114
1 vote

Is Relativistic GAN better than WGAN-GP?

For anyone looking for answer, as explained in Paper: The relativistic discriminator: a key element missing from standard GAN!, Yes, Standard RaGAN with gradient penalty generate data of better ...
SANJAY BHANDARI's user avatar
1 vote

What is being optimized with WGAN loss? Is the generator maximizing or minimizing the critic value?

I think I understand what's happening with the loss functions now. Notation: D = discriminator/critic G = generator D(x) - Critic score on real data D(G(z)) - Critic score on fake data ∇_D - Critic ...
Gabriel Mongaras's user avatar
1 vote

Why do we use a linear interpolation of fake and real data to penalize the gradient of discriminator in WGAN-GP

In [1], section 4, the authors mention the following: Sampling distribution We implicitly define $p_{\hat{x}}$ sampling uniformly along straight lines between pairs of points sampled from the data ...
Eduardo Montesuma's user avatar

Only top scored, non community-wiki answers of a minimum length are eligible