Questions tagged [wasserstein-gan]
For questions related to the Wasserstein GAN, introduced in "Wasserstein Generative Adversarial Networks" (2017, PMLR) by Martin Arjovsky et al.
17
questions
0
votes
1
answer
37
views
Do WGAN gradients require multi-variable calculus?
The generator tries to maximise this function D(G(z)). That much I understand.
But how can the critic maximise D(x) - D(G(z)). ...
- 13
2
votes
0
answers
325
views
GAN : Why does a perfect discriminator mean no gradient for the generator?
In the training of a Generative Adversarial Networks (GAN) system, a perfect discriminator (D) is one which outputs 1 ("true image") for all images of the training dataset and 0 ("false ...
- 221
0
votes
0
answers
37
views
Why would one still use a traditional GAN architecture or WGAN architecture instead of a WGAN-GP architecture?
I've been diving into the literature of GANs, and quite early on, I was pretty convinced that WGAN-GPs were the way to go. The WGAN-GP architecture is, as far as I know, theoretically and empirically ...
- 2,083
0
votes
2
answers
294
views
Is Relativistic GAN better than WGAN-GP?
I am currently reading the ESRGAN paper and I noticed that they have used Relativistic GAN for training discriminator. So, is it because Relativistic GAN leads to better results than WGAN-GP?
2
votes
1
answer
735
views
What is being optimized with WGAN loss? Is the generator maximizing or minimizing the critic value?
I am kind of new to the field of GANs and decided to develop a WGAN. All of the information online seems to be kind of contradicting itself. The more I read, the more I become confused, so I'm hoping ...
2
votes
1
answer
370
views
Why do we use a linear interpolation of fake and real data to penalize the gradient of discriminator in WGAN-GP
I'm trying to better frame/summarize the formulations and motivations behind Wasserstein GAN with gradient penalty, based on my understanding.
For the basic GAN we are trying to optimize the following ...
- 307
0
votes
0
answers
234
views
Possible improvements to WGAN-GP output images
I am mapping rather complex data into what essentially amounts to a greyscale image to take better advantage of GANs for generative means. Here is an example of some real data:
All real data is of ...
- 1
0
votes
1
answer
722
views
How to calculate the gradient penalty proposed in "Improved Training of Wasserstein GANs"?
The research paper titled Improved Training of Wasserstein GANs proposed a gradient penalty in order to avoid undesired behavior due to weight clipping of the discriminator.
We now propose an ...
- 3,612
0
votes
1
answer
738
views
What to do with a GAN that trained well but got worse over time?
I am training a WGAN-GP network based on the following paper, though I am using a different dataset. Now, for the first ~ 60-70 epochs, my network trained really well, which I could see in the loss ...
- 171
1
vote
0
answers
47
views
How can I estimate the minimum number of training samples needed to get interesting results with WGAN?
Let's say we have a WGAN where the generator and critic have 8 layers and 5 million parameters each. I know that the greater the number of training samples the better, but is there a way to know the ...
2
votes
1
answer
94
views
Classifying generated samples with Wasserstein-GAN as real or fake
I'm quite new to GANs and I am trying to use a Wasserstein GAN as an augmentation technique. I found this article
https://www.sciencedirect.com/science/article/pii/S2095809918301127,
and would like to ...
- 21
2
votes
1
answer
280
views
Aren't scores in the Wasserstein GAN probabilities?
I am quite new to GAN and I am reading about WGAN vs DCGAN.
Relating to the Wasserstein GAN (WGAN), I read here
Instead of using a discriminator to classify or predict the probability of generated ...
- 183
5
votes
1
answer
1k
views
Wasserstein GAN: Implemention of Critic Loss Correct?
The WGAN paper concretely proposes Algorithm 1 (cf. page 8). Now, they also state what their loss for the critic and the generator is.
When implementing the critic loss (so lines 5 and 6 of Algorithm ...
- 171
1
vote
0
answers
152
views
WGAN-GP Loss formalization
I have to write the formalization of the loss function of my network, built following the WGAN-GP model. The discriminator takes 3 consecutive images as input (such as 3 consecutive frames of a video) ...
- 111
3
votes
1
answer
531
views
What is the reason for mode collapse in GAN as opposed to WGAN?
In this article I am reading:
$D_{KL}$ gives us inifity when two distributions are disjoint. The value of $D_{JS}$ has sudden jump, not differentiable at $\theta=0$. Only Wasserstein metric provides ...
- 131
1
vote
0
answers
40
views
Under what conditions can one find the optimal critic in WGAN?
The Kantorovich-Rubinstein duality for the optimal transport problem implies that the Wasserstein distance between two distributions $\mu_1$ and $\mu_2$ can be computed as (equation 2 in section 3 in ...
- 41
1
vote
0
answers
32
views
Wasserstein GAN with non-negative weights in the critic
I want to train a WGAN where the convolution layers in the critic are only allowed to have non-negative weights (for a technical reason). The biases, nonetheless, can take both +/- values. There is no ...
- 41