Questions tagged [generative-adversarial-networks]

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.

Filter by
Sorted by
Tagged with
5
votes
0answers
31 views

Why is my GAN more unstable with bigger networks?

I am working with generative adversarial networks (GANs) and one of my aims at the moment is to reproduce samples in two dimensions that are distributed according to a circle (see animation). When ...
1
vote
0answers
37 views

Why don't those developing AI Deepfake detectors use two detectors at once so as to catch deepfakes in one or the other?

Why don't those developing AI Deepfake detectors use two differently trained detectors at once that way if the Deepfake was trained to fool one of the detectors the other would catch it and vice-versa?...
2
votes
1answer
42 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 ...
1
vote
1answer
40 views

What dataset might Elon Musk's Dall-E have used?

Dall-E, it can generate many imaginative images from the description, even some peculiar images, how did they actually create this kind of dataset to train this AI , because there is not much of that ...
1
vote
1answer
22 views

In this implementation of pix2pix, why are the weights for the discriminator and generator losses set to 1 and 100 respectively?

I am working on a pix2pix GAN model that was inspired by the code in this Github repository. The original code is working and I have already customized most of the code for my needs. However, there is ...
7
votes
1answer
77 views

What are the fundamental differences between VAE and GAN for image generation?

Starting from my own understanding, and scoped to the purpose of image generation, I'm well aware of the major architectural differences: A GAN's generator samples from a relatively low dimensional ...
0
votes
0answers
9 views

Parametrizing non-analytical functions using generative models

My questions centers around what method is best to use parametrize a response function for an experiment. We are currently using ab initio simulation to model our experiment's response. Unfortunately, ...
0
votes
1answer
39 views

How is the latent vector transforming to a feature map in DCGAN (Generator structure)?

I'm working on the code trying to generate new images using DCGAN model. The structure of my code is from the PyTorch tutorial here. I'm a bit confused trying to find and understand how the latent ...
3
votes
2answers
117 views

Mathematical Analysis of the Loss function of GAN

I was pondering on loss function of GAN and following thing turned out \begin{aligned} L(D, G) & = \mathbb{E}_{x \sim p_{r}(x)} [\log D(x)] + \mathbb{E}_{x \sim p_g(x)} [\log(1 - D(x)] \\ & =...
3
votes
0answers
45 views

Can someone explain R1 regularization function in simple terms?

I'm trying to understand the R1 regularization function, both the abstract concept and every symbol in the formula. According to the article, the definition of R1 is: It penalizes the discriminator ...
1
vote
1answer
27 views

Optimum Discriminator for label smoothed GAN

I was reading the paper called Improved Techniques for Training GANs. And, in the one-sided label smoothing part, they said that optimum discriminator with label smoothing is $$ D^*(x)=\frac{\alpha \...
0
votes
1answer
47 views

Why is it easier to construct adversarial examples relative to training neural networks?

I was having looking at this lecture by Ian Goodfellow and my doubt is around 18:00 timestamp where he explains generation of adversarial examples using FGSM. He mentions that the there is a linear ...
5
votes
0answers
55 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 ...
1
vote
2answers
74 views

Recent deep learning textbook (i.e. covering at least GANs, LSTM and transformers and attention)

I am searching for an academic (i.e. with maths formulae) textbook which covers (at least) the following: GAN LSTM and transformers (e.g. seq2seq) Attention mechanism The closest match I got is Deep ...
2
votes
0answers
43 views

Hairstyle Virtual Try On

I want to help people with cancer who are under chemotherapy, and generally people who have lost their hair to Virtually Try-On Toupees/Wigs on their head. VTO must support both the frontal and side ...
10
votes
1answer
128 views

Can I start with perfect discriminator in GAN?

In many implementations/tutorials of GANs that I've seen so far (e.g. this), the generator and discriminator start with no prior knowledge. They continuously improve their performance with training. ...
1
vote
0answers
16 views

How does noise input size affect fake image generation with GANs?

In Generative Adversarial Networks, the Generator takes noise vector as input and feeds it forward to create an image. The noise vector consists of random numbers sampled from the normal distribution. ...
2
votes
1answer
36 views

What do they mean by “contradictory loss”?

In page 4 of the paper https://arxiv.org/pdf/2009.07047v1.pdf, it says the encoder $E_{R,X}$ of $VAE_1$ tries to fool the discriminator with a contradictory loss to ensure that $R$ and $X$ are mapped ...
0
votes
0answers
28 views

Why using Aux() to implement VAE_1?

I have a bit of difficulties working on the article :https://arxiv.org/pdf/2009.07047v1.pdf. I want to implement the VAE_1, but it used VAE-GAN. I am familiar with ...
2
votes
0answers
102 views

Generating fake faces containing specific features with GANs

I'm trying to understand how DeepFakes are generated and so far I understood that they're mostly generated through the usage of GANs and autoencoders. The autoencoders part is understandable, but what ...
1
vote
1answer
28 views

Why do we need to provide false labels to the discriminator on purpose to train GANs?

This is the tutorial that I used to learn about GANs. In this tutorial, it taught us to intentionally provide false labels to "fool" the discriminator, but does it make the discriminator ...
1
vote
1answer
29 views

GAN model predictions before training is predictable

I have a dataset of 3000 8x8 images, and I would like to train a GAN for an image generation purpose. I am planning to start with a simple GAN model and see if it overfits. Before training, I try to ...
1
vote
1answer
39 views

Explain the difference in graphical patterns between discriminator fake loss and generator loss in GAN

In GAN (generative adversarial networks), let us take "binary cross-entropy" as the loss function for discriminator $$(overall \; loss = -\sum log(D(x_i)) -\sum log(1-D(G(z_i))) $$ $$ where \...
1
vote
0answers
33 views

In the MINE paper, why is $\hat{G}_B$ biased, and how does the exponential moving average reduce the bias?

While reading the Mutual Information Neural Estimation (MINE) paper [1] I came across section 3.2 Correcting the bias from the stochastic gradients. The proposed method requires the computation of the ...
1
vote
0answers
28 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) ...
1
vote
0answers
87 views

SeqGAN - Policy gradient objective function interpretation

Could someone clear my doubt on the loss function used in SeqGAN paper . The paper uses policy gradient method to train the generator which is a recurrent neural network here. Have I interpreted the ...
0
votes
0answers
26 views

Wasserstein GAN with gradient penality - Loss values

I have trained a WAN with gradient penalty and the loss values ​​seem to me much higher than the examples I have seen on the net. The generator receives 2 images as input and must generate a ...
2
votes
0answers
34 views

How to define loss function for Discriminator in GANs?

To train the discriminator network in GANs we set the label for the true samples as $1$ and $0$ for fake ones. Then we use binary cross-entropy loss for training. Since we set the label $1$ for true ...
0
votes
2answers
65 views

What is the right way to train a generator in a GAN?

I am not fully understanding how to train a GAN's generator. I have a few questions below, but let me first describe what I am doing. I am using the MNIST dataset. I generate a batch of random images ...
1
vote
0answers
25 views

GAN for specific face attribute modification

A recent paper "MagGAN High Resolution Face Attribute Editing with Mask Guided GAN" published this month (October 2020) describe how an approach has been developed to deal with specific face ...
0
votes
0answers
27 views

How to optimize my GAN generator and discriminator models' structures?

I'm using Tensorflow to feed a DCGAN 3000 320x320 colored images of cars. The goal is to generate new cars. I've been training on Google Colab for the past 10 hours or so. I guess I can expect results ...
1
vote
0answers
27 views

Why scaling down the parameter many times during training will help the learning speed be the same for all weights in Progressive GAN?

The title is one of the special things in Progressive GAN, a paper of the NVIDIA team. By using this method, they introduced that Our approach ensures that the dynamic range, and thus the learning ...
2
votes
0answers
49 views

What is the purpose of the DAMSM loss for the generators in AttnGAN?

I am confused about the training part in AttnGan. If you observe page 3. There are two types of losses for generator network: one involving the Deep Attentional Multimodal Similarity Model (DAMSM) ...
0
votes
1answer
37 views

Is there any network/paper used to analyse music scores?

As I am curious on music theory I would like to know that If is there any such network that analyse like labeling chords, or doing a roman numeral analysis. Like an example below: Source It does not ...
6
votes
2answers
133 views

Why don't we use auto-encoders instead of GANs?

I have watched Stanford's lectures about artificial intelligence, I currently have one question: why don't we use autoencoders instead of GANs? Basically, what GAN does is it receives a random vector ...
3
votes
1answer
44 views

Why is the mean used to compute the expectation in the GAN loss?

From Goodfellow et al. (2014), we have the adversarial loss: $$ \min_G \, \max_D V (D, G) = \mathbb{E}_{x∼p_{data}(x)} \, [\log \, D(x)] \\ \quad\quad\quad\quad\quad\quad\quad + \, \mathbb{E}_{z∼p_z(...
1
vote
1answer
26 views

Does a better discriminator in GANs mean better sample generation by the generator?

Since the discriminator defines how the generator is updated, then building a discriminator with a higher number of parameters/more layers should lead to a better quality of generated samples. So, ...
0
votes
0answers
11 views

Generative Adversarial Network with two images in input

I am doing an internship project regarding deep learning, and it is a totally new topic for me as I have never studied machine learning in the bachelor's degree courses. I have to implement a GAN that ...
0
votes
0answers
17 views

Conditional GAN on harder datasets

I have seen conditional GANs often applied to easier datasets like MNIST and CIFAR-10 to reasonable success, but at the same time these datasets are simple enough that naïve CNNs can fairly easily max ...
0
votes
0answers
22 views

How Discriminator and Generator weights are adjusted in conditional Generative adversarial networks proposed by Isola et al. ? (in simple terms)

Can someone please explain to me the complete architecture of cGANs as mentioned here. I am confused as "ref" is not defined in the whole article. I am sorry if you find the question silly. ...
2
votes
0answers
39 views

How to overfit GANs with a single image

When designing CNN for image recogition a commonly used sainty check to see if a model is working/designed fine is to see if we are able to overfit the model with a very small subset of images. I am ...
3
votes
1answer
91 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 ...
5
votes
1answer
102 views

Can GANs be used to generate something other than images?

AFAIK, GANs are used for generating/synthesizing near-perfect human faces (deepfakes), gallery arts, etc., but can GANs be used to generate something other than images?
0
votes
0answers
38 views

How to match faces with images in ID proofs

I'm working on a problem to identify whether a person's image matches with the one in his ID proof. The inputs are the real-time face image and scanned ID proof. Options that I'm thinking of Prepare ...
0
votes
0answers
57 views

Need to determine a ML solution for the given graphical problem

I need to generate a 3D plane given a set of feature inputs. Most inputs are a range of values between 0 and 1 (sigmoidial), except a few. For example a rectangle: ...
0
votes
0answers
27 views

How do I get my DCGAN to generate a number of fake images?

I have a Deep Convolutional Generative Adversarial Network (DCGAN) that trains on the CIFAR dataset. When I finish the training (100k epochs), how can I make my network generate 1000 fake images? I ...
1
vote
0answers
31 views

Concrete example of how transposed convolutions are able to *add* features to an image

Say we have a simple gray scale image. If we use a filter which is just the 3x3 identity matrix (or more pointedly the identity matrix but with -1 instead of the 0 entries), it is fairly easy to see ...
1
vote
0answers
28 views

Do GANs also learn to map between the distribution from which the random noise is sampled and the true distribution of the data?

I am reading about GANs. I understand that GANs learn implicitly the probability distribution that generated the data. However, at the input we give a random noise vector. It seems that we can sample ...
1
vote
1answer
42 views

Is GAIL applicable if the expert's trajectories are for the same task but are in a different environment?

Is the GAIL applicable if the expert's trajectories (sample data) are for the same task but are in a different environment (modified but will not be completely different)? My gut feeling is, yes, ...
1
vote
1answer
52 views

Why does my “entropy generation” RNN do so badly?

I'm new to relatively RNNs, and I'm trying to train generative and guessing neural networks to produce sequences of real numbers that look random. My architecture looks like this (each "circle&...