For questions related to generative adversarial networks (GANs), introduced in the paper Generative Adversarial Nets (2014) by J. Goodfellow et al. A GAN is composed of a discriminative model (D) and a generative model (G). The discriminator D needs to distinguish between data generated by the generator G and data in the training set, while the generator G needs to generate data such that the discriminator D is not able to accomplish its task.

215 questions
Filter by
Sorted by
Tagged with
61 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 ...
1 vote
37 views

Is there a name for this model?

I have an image autoencoder model trained as follows: Step 1) train a GAN to obtain a generator capable of drawing from the data manifold by sampling a normal distribution in latent space Step 2) ...
39 views

What is the meaning of $p_{\text {data }}(y)$ in the CycleGAN?

In the original CycleGAN paper, on the second page, there is a sentence that I didn't quite understand In theory, this objective can induce an output distribution over $\hat{y}$ that matches the ...
63 views

What is the domain of the discriminator of a GAN?

I've read that the discriminator $D$ validates an image $D(x)$, where $x$ is either a real image or a fake one created by the generator, i.e. $D(G(x))$. What does the function of the discriminator ...
28 views

Why do we train the discriminators k times but train the generator only 1 time in a iteration in GAN?

In this paper https://arxiv.org/abs/1406.2661 , the codes for training a gan are : Why do we train the discriminator for $k$ steps while the generator only for $1$ step? Why not the other way around?
• 3
51 views

How to combine an image and a set of parameters as input to a GAN?

I have worked with a few GAN-like algorithms, but always with similar inputs and outputs. Being only a novice in deep learning, I often work by adapting an already existing Notebook, but today I have ...
14 views

Why even-sized kernels are used in upscaling layers?

I have noticed that UNet and many GANs uses even-sized kernels in the upscale part of the model. I have read that at least in the GAN situation one of the reasons why we use even-sized kernels is that ...
38 views

Why do we use the same parameters for the joint, marginal and conditional distributions in VAEs?

I've noticed in several resources on variational autoencoders (for example the wikipedia article), we use the same parameters theta for the prior, likelihood, posterior, etc distributions. For example ...
• 21
20 views

What are the benefits of using multiple convolutions, as opposed to one, before the pooling layer in a U-Net?

I have seen U-Nets that use a single convolution before the pooling operator and some that use two or more. My question is, what is better? Or what are the benefits of using more or less convolutions?
22 views

Is the "Helvetica scenario" mentioned here related to Artificial Intelligence?

Consider the following sentence from the original GAN paper titled Generative Adversarial Nets in particular, $G$ must not be trained too much without updating $D$, in order to avoid "the ...
• 3,099
19 views

Why GAN is not as useful in tabular settings

This is inspired by a previous question Why are GAN models not heavily used for NLP? One answer says that the GAN is not as useful outside the image domain. Recently my friend and I are trying it out ...
48 views

Training a GAN after after evaluation metric reaches minimum

I am training a StyleGAN-3 using one of the pre-trained models. At some point, roughly halfway through the 5000 kimg recommended for fine-tuning, the FID50K score starts oscillating around a minimum ...
1 vote
38 views

• 11
35 views

Is it impossible to evaluate the generator distribution directly?

The following excerpt is taken from 3. The Inception Score for Image Generation from the paper titled A Note on the Inception Score. Suppose we are trying to ...
• 3,099
41 views

What is meant by inverting the generator?

Generative Adversarial Networks, in general, consists of two multi layer perceptrons: generator and discriminator. Generator is used for generating samples that are as real as training samples and ...
• 3,099
29 views

How did authors ensure that critical points do exist in GAN?

Using an MLP as a generator introduces multiple critical points in parameter space. You can read this excerpt from the research paper titled Generative Adversarial Nets by Ian J. Goodfellow et al. In ...
• 3,099
1 vote
44 views

When can we call a loss function "adaptive"?

A loss function is a measure of how bad our neural network is. We can decrease the loss by proper training. I came across the phrase "adaptive loss function" in several research papers. For ...
• 3,099
1 vote
21 views

Is the following a typo or am I understanding wrongly regarding discriminator?

Consider the following paragraph from the section 3: Background of the research paper titled Generative Adversarial Text to Image Synthesis by Scott Reed et al. ...
• 3,099