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
2
votes
0answers
47 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
79 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
35 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
47 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
23 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
25 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
22 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 ...
0
votes
0answers
26 views

Generalizability of Generative Adversarial Imitation Learning (GAIL) method

I have something would like to clarify regarding Generative Adversarial Imitation Learning (GAIL). Is the original GAIL applicable if the experts trajectories (sample data) are for the same task but ...
1
vote
1answer
39 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&...
0
votes
0answers
24 views

Can StyleGAN be refined without a full training?

Can I refine StyleGAN or StyleGAN2 without retraining it for many days, such that its pretrained model is trained to generate only faces similar to a (rather small) set of reference images? I would ...
0
votes
1answer
205 views

After a GAN is trained, which parts of it are used to generate new outputs from data?

After a GAN is trained, which parts of it are used to generate new outputs from data? Options are: Neither Discriminator Generator Both Generator and Discriminator
1
vote
0answers
41 views

Will adding memory to a supervised learning system makes it into a Bayesian learning system?

Seung et.al recently published GameGAN paper, GameGAN learned and stored the whole Pacman game and was able to reproduce it without a game engine. The uniqueness of GameGAN is that it had added memory ...
0
votes
0answers
32 views

How GAN generator produce integer RGB colored picture?

For traditional neural networks, I know that we can't constraint the output to be strict integers. My question is what technique does GANs use to produce integer outputs, that can be then converted to ...
1
vote
0answers
20 views

Is the generator distribution in GAN's continuous or discrete?

I have some trouble with the probability densities described in the original paper. My question is based on Goodfellow's paper and tutorial, respectively: Generative Adversarial Networks and NIPS ...
1
vote
0answers
25 views

What does it mean when the discriminator's loss gets a constant value while the generator's loss keeps on changing?

While training a GAN-based model, every time the discriminator's loss gets a constant value of nearly 0.63 while the generator's loss keeps on changing from 0.5 to 1.5, so I am not able to understand ...
1
vote
0answers
21 views

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 $$W(\mu_1,\mu_2)=\underset{f\...
1
vote
0answers
36 views

Why is this GAN not converging?

This GAN being trained with CelebA dataset doesn't seem to mode collapse, discriminator is not really over confident, and yet the quality is stuck on these rough Picasso-like generator images. Using ...
1
vote
0answers
26 views

Training Conditional DCGAN with GAN-CLS loss

I am trying to implement conditional GAN using GAN-CLS loss as described in paper: https://arxiv.org/abs/1605.05396 So, while training discriminator, I should I have three batches of data: [...
0
votes
0answers
16 views

How would one modify CycleGAN in order to map a distribution to itself?

CycleGAN can map between two different distributions $X$ and $Y$ with cycle consistency. This is done with generator functions $F: X \mapsto Y$ and $G: Y \mapsto X$, such that $||G(F(x)) - x||_1 \...
1
vote
0answers
12 views

Using DCGAN on a (very small) dataset of art

I am developing a DCGAN using the this tutorial in PyCharm. As my usage of this tutorial suggests, I am quite new to DCGANs as I've previously only had a few experiences with machine learning ...
1
vote
0answers
15 views

How would semantic segmentation work with a non convolutional neural network

Listening to lectures, convolutional neural network seems to be an improvement over a simple neural network, where for example, you take every pixel in the image, flatten it to a vector, and feed it ...
2
votes
0answers
27 views

How should I design a reward function for a NLP problem where two models interoperate?

I would like to design a reward function. I am training two models from the first model that classify set of texts (paragraphs and keywords) and I also got some hidden states. The second model is ...
1
vote
0answers
35 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
24 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
41 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? ...
1
vote
0answers
51 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?
2
votes
0answers
39 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
43 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
30 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
38 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
23 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
14 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
13 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
49 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
72 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 ...
1
vote
0answers
28 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
99 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
80 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 ...
2
votes
0answers
574 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-...
3
votes
1answer
114 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
91 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
101 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
88 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 ...
4
votes
1answer
70 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
55 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
95 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
51 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
56 views

Why does the discriminator minimize the cross-entropy while the generator maximize it?

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
23 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 ...