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
0
votes
0answers
8 views

Advice for a beginner with mathematics/electrical engineering background [closed]

I don't really know if somebody else already asked something related or if it is a duplicate. I'm an engineering student with a general background (French École + Regular EECS Brazillian University ...
1
vote
0answers
23 views

What are some real-world products or applications that can be developed using GANs?

GANs have shown good progress across a wide variety of domains ranging from image translation, image generation, text to image synthesis, audio/video generation, image super-resolution and many more. ...
1
vote
1answer
13 views

What does “shape information” mean in terms of GAN(generative adversarial networks)?

A paper says However, annotations used as inputs to C-GAN are typically based only on shape information, which can result in undesirable intensity distributions in the resulting artificially-...
1
vote
1answer
34 views

What does equation in the “related work” section of the GAN paper mean?

I was going through the paper on GAN by Ian Goodfellow. Under the related work section, there is an equation. I cannot decipher the equation. Can anyone help me understand the meaning of the equation? ...
0
votes
0answers
30 views

What is the difference between using dense layers as opposed to convolutional layers in my networks when dealing with images?

I am thinking about developing a GAN. What is the difference between using dense layers as opposed to convolutional layers in my networks when dealing with images?
1
vote
0answers
25 views

Why does GAN loss converge to log(2) and not -log(2)?

In Goodfellow's paper, he says: Hence, by inspecting Eq. 4 at $D^*_G (\mathbf{x}) = \frac{1}{2}$, we find $C(G) = \log \frac{1}{2}+ \log \frac{1}{2} = − \log 4$. To see that this is the best ...
2
votes
1answer
31 views

Am I overfitting my GAN model?

I'm training a DCGAN model on a 320x320 dataset of images and after an hour of training the generator started to generate (on the same latent space noise as during training) images that are identical ...
1
vote
1answer
21 views

GANs: Should Generator update weights when Discriminator says false continuously

My GANs is like this: Train an autoencoder (VAE), get the decoder part and use as Generator Train Discriminator After training, do the generation in these steps: Call Generator to generate an image ...
2
votes
1answer
31 views

Have GANs been used to solve regression problems?

I've noticed that in the last 2 years GANs have become really popular. I know that initially they have been proposed for image classification but I was curious if any of you are aware of any papers ...
1
vote
0answers
20 views

Which generative methods are better for generating graphs, while preserving node and edge labels?

I started to dig into the topic of graph generation and I have a question - which out of generative methods (autoregressive, variational autoencoders, GANs, any other?) are better for generating ...
1
vote
0answers
9 views

Generation of realistic real-valued sequences using Wasserstein GAN fails

My goal is to generate artificial sequences of real-valued data (e.g. time series) with GANs. Starting simple I tried to generate realistic sine-waves using a Wasserstein GAN. But even on this simple ...
0
votes
0answers
8 views

Architecture of the encoder in a Bi-GAN?

I know this is a subjective question, but I was thinking how does one decide on their encoder architecture in the case of Bi-directional GANs. The first idea coming to my mind is basically mirroring ...
2
votes
2answers
40 views

Is it feasible to use GAN for high-quality image synthesis other than human faces?

The famous Nvidia paper Progressive Growing of GANs for Improved Quality, Stability, and Variation, the GAN can generate hyperrealistic human faces. But, in the very same paper, images of other ...
6
votes
1answer
59 views

How does the generator in GAN's work?

After reading a lot of articles (for instance, this one - https://developers.google.com/machine-learning/gan/generator), I've been wondering: how does the generator in GAN's work? What is the input ...
0
votes
0answers
18 views

What is the need for Auxiliary Decoder in the VAE-GAN?

The below image taken from Tim Sainberg's GitHub repo (https://github.com/timsainb) shows the structure of a VAE-GAN: My question is about the second row in the diagram. Random samples drawn from z ...
0
votes
0answers
21 views

Reversing A Keras Dense GAN

I have a Keras GAN where every layer in the generator has more neurons than the last and also where they all have an activation of LeakyReLU(alpha=0.1). I am trying to map the image back to the noise ...
1
vote
1answer
61 views

CycleGAN for paired data

I am very interested in the application of CycleGANs. I understand the concept of unpaired data and it makes sense to me. But now a question comes to my mind: what if I have enough paired image data, ...
2
votes
2answers
65 views

What makes GAN or VAE better at image generation than NN that directly maps inputs to images

Say a simple neural network's input is a collection of tags (encoded in some way), and the output is an image that corresponds to those tags. Say this network consists of some dense layers and some ...
1
vote
0answers
244 views

How many training data required for GAN?

I'm beginning to study and implement GAN to generate more dataset. I'll just try to experiment with state-of-the-art GAN models as described in here https://paperswithcode.com/sota/image-generation-on-...
2
votes
1answer
96 views

Why AI is (or not) a good option for the generation of random numbers?

Why AI is (or not) a good option for the generation of random numbers? Would GANs be suited for this purpose?
2
votes
0answers
41 views

How does deepfake technology work with multiple people in a single frame?

I was watching this video from corridor crew, according to them, they have used deepfake technology to create this video. I myself have never made a deepfake videos, but I have enough knowledge in the ...
5
votes
1answer
81 views

Context-based gap-fill face posture-mapper GAN

These images are handmade, not auto-generated like they will be in production. Apologies for inaccuracies in the graph overlay. I am trying to build an AI like that displayed in the diagram: when ...
5
votes
1answer
79 views

Isn't deep fake detection bound to fail?

Deep fakes are a growing concern: the ability to credibly alter a video may have great (negative) impacts on our society. It is so much of a concern, that the biggest tech companies launched a ...
3
votes
1answer
41 views

Why does a Lipschitz continuous discriminator in GANs assure statistical boundedness?

I have been reading the paper which introduced spectral normalization in GANs. At some point the paper mentions the following: The machine learning community has been pointing out recently that ...
2
votes
1answer
44 views

How exactly does adversarial training help in handling mode-collapse in generative networks?

Of my understanding mode-collapse is when there happen to be multiple classes in the dataset and the generative network converges to only one of these classes and generates images only within this ...
4
votes
1answer
53 views

Why is Jensen-Shannon divergence preferred over Kullback-Leibler divergence in measuring the performance of a generative network?

I have read articles on how Jensen-Shannon divergence is preferred over Kullback-Leibler in measuring how good a distribution mapping is learned in a generative network because of the fact that JS-...
2
votes
0answers
44 views

How to implement loss function of H-GAN model

I was trying to implement the loss function of H-GAN. Here is my code . But it seem somethings wrong, maybe is recognition loss on z (EQ 9). I used the EQ 5 on MISO to calculate it. Here is my code: ...
1
vote
1answer
49 views

Trying to understand the math of GANs with Goodfellows paper and tutorial

In his original GAN paper Goodfellow gives a game theoretic perspective for GANs: \begin{equation} \underset{G}{\min}\, \underset{D}{\max}\, V\left(D,G \right) = \mathbb{E}_{x\sim\mathit{p}_{\...
2
votes
0answers
22 views

How to train a transformer text-to-text model on counterexamples?

Is it possible to update the weights of a vanilla transformer model using counterexamples alongside examples? For example, from the PAWS data set, given the phrases "Although interchangeable, the ...
1
vote
0answers
14 views

Looking for GAN paper with spiral image

I am looking for a GAN paper I have read a while ago, but unfortunately cannot find it again. I think it compared GANs and other methods (like CVAEs) w.r.t. how they handle multi-modal data, not sure ...
1
vote
0answers
43 views

Is there a GAN that can be used for sequence prediction?

I want to use a GAN for sequence prediction, in a similar way that we use RNNs for sequence prediction. I want to test its performance in comparison with RNNs. Is there a GAN that can be used for ...
0
votes
0answers
16 views

Numbers to image regression

I would like to create a machine learnig framework that could predict the 3D heat distribution of a room(of size 120x120x120) , given multiple parameters(position of the heater, orientation, power of ...
1
vote
0answers
70 views

Which approaches are best suited for text deblurring?

I want to deblur text images using deep learning. Which approaches are best suited for the task? Any example networks? Is unsupervised network the best approach? GAN or cycle GAN for these purposes? ...
1
vote
0answers
9 views

How does InfoGAN learn latent categorical codes on MNIST

While reading the InfoGAN paper and implement it taking help from a previous implementation, I'm having some difficulty understanding how it learns the discrete categorical code when trained on MNIST. ...
2
votes
1answer
36 views

How to generate the original image from feature set?

We all know that using CNN, or even simpler functions, like CLD or EHD, we can generate a set of features out of images. Is there any ways or approaches that given a set of features, we can somehow ...
1
vote
0answers
30 views

Is convergence to a local minima more likely with transfer learning?

While doing transfer learning where my two problems are face-generation and car-generation is it likely that, if I use the weights of one problem as the initialization of the weights for the other ...
1
vote
0answers
79 views

Could the Jensen-Shannon divergence and Kullback-Leibler divergence be used as loss functions of non-generation problems?

If I understand correctly, the KL divergence is a measure of information loss between a ground truth distribution $P$ and a predicted distribution $Q$, and the Jensen-Shannon divergence is the mean of ...
2
votes
1answer
78 views

What is the purpose of the noise injection in the generator network of a GAN?

I do not understand why with enough training how the generator cannot learn all images from the training set as a mapping from the latent space - It is the absolute optimal case in training as it ...
0
votes
1answer
149 views

Query regarding the minmax loss function formulation of the training of a Generative Adversarial Network (GAN)

Just needed a clarification on the training procedure for a standard GAN. Of my understanding the loss function to optimize is a min max (max min causing mode collapse due to focus on one class ...
0
votes
1answer
59 views

If the goal of training of a GAN is to have $P_g=P_{data}$, shouldn't this produce the exact same images?

Referring to the blog, Image Completion with Deep Learning in TensorFlow, it clearly says that we would want a generator $g$ whose modeled distribution fits our dataset $data$, in other words, $P_{...
0
votes
0answers
45 views

Why following GAN is not working:

Trying to see, why my big GAN project is not working, i created the small GAN project to see interaction of generator and discriminator. Dummy input is like: ...
1
vote
0answers
34 views

Is it possible to use adversarial training to learn invariant features?

Given a set of time series data that are generated from different sites where all sites are investigating the same objective but with slightly different protocols. Is it possible to use adversarial ...
3
votes
1answer
24 views

What parameters can be tweaked to avoid a generator or discriminator loss collapsing to zero when training a DC-GAN?

Sometimes when I am training a DC-GAN on an image dataset, similar to the DC-GAN PyTorch example (https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html), either the Generator or ...
0
votes
0answers
22 views

Not clear about CoordConv

I read the CoordConv paper and I am a bit confused about its implementation for a GAN/VAE. I understand how to add 2 more channels to an image and pass that to a conv net (and there are good online ...
3
votes
1answer
121 views

How is G(z) related to x in GAN proof?

In the proofs for the original GAN paper, it is written: $$∫_x p_{data}(x) \log D(x)dx+∫_zp(z)\log(1−D(G(z)))dz =∫_xp_{data}(x)\log D(x)+p_G(x) \log(1−D(x))dx$$ I've seen some explanations asserting ...
0
votes
0answers
25 views

DCGAN loss determining data normalization problems

I'm working with a DCGAN, a deep CNN for classifying images with a GAN that competes with the classifier to generate images of what we are classifying. The goal of the project at the moment is to ...
2
votes
0answers
17 views

How important is architectural similarity between the discriminator and generator of a GAN?

Shouldn't the discriminator and generator work fine even if they don't process data symmetrically? I mean, they don't only receive the final layer results of each other, they don't use data that from ...
1
vote
1answer
54 views

Why is expectation used instead of simple sum in GANs?

Why do GAN loss functions use expectation(sum + division) instead of a simple sum?
2
votes
0answers
38 views

Can GANs be used to generate matching pairs to inputs?

I have some limited experience with MLPs and CNNs. I am working on a project where I've used a CNN to classify "images" into two classes, 0 and 1. I say "images" as they are not actually images in the ...
0
votes
0answers
27 views

Deep Generative Networks Probability of “Success”

I have built various "successful" GANs or VAEs that can generate realistic images reliably, but in either case the generative step is sampling a latent feature vector from some distribution and ...