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.

94 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
7
votes
0answers
68 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 ...
5
votes
0answers
103 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 ...
4
votes
0answers
37 views

Are generative models actually used in practice for industrial drug design?

I just finished reading this paper MoFlow: An Invertible Flow Model for Generating Molecular Graphs. The paper, which is about generating molecular graphs with certain chemical properties improved the ...
4
votes
0answers
2k 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
0answers
37 views

Best Machine Learning Model for “Predicted” Image Generation

I am currently working on undergraduate research to determine hotspots for hand-surface contact. Ideally, I would like to give the model a depth image as input: Example of synthetic depth image and ...
3
votes
0answers
45 views

Is the GAN architecture better suited for medical image denoising than the CNN?

I'm considering using GANs for medical image denoising, based on previous literature, like this and this. My input to the GAN would be a high-noise image and my ideal output would be a low-noise, high-...
3
votes
1answer
382 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 ...
3
votes
0answers
35 views

How do GANs create an image with specific characteristics?

I've seen GANs that do things like convert an image to a painting or this GAN here https://make.girls.moe/#/ that takes in a set of characteristics and generates a waifu with those characteristics. ...
2
votes
0answers
38 views

How does the output distribution of a GAN change if the parameters are slightly purturbed?

Suppose $G_{\phi}:\mathcal{Z}\rightarrow \mathcal{X}$ is a generator (neural network, non-invertible) that can sample from some distribution $\pi$ on $\mathcal{X}$. That is, $G_{\phi}(z)\sim \pi$ when ...
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 ...
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 ...
2
votes
0answers
91 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) ...
2
votes
0answers
31 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 ...
2
votes
0answers
79 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
0answers
380 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 ...
2
votes
0answers
55 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: ...
2
votes
0answers
26 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 ...
2
votes
0answers
11 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
0answers
21 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 ...
2
votes
0answers
43 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 ...
2
votes
0answers
60 views

Transposed convolution as upsampling in DCGAN

I read several papers and articles where it is suggested that transposed convolution with 2 strides is better than upsampling then convolution. However implementing such model with the transposed ...
2
votes
1answer
232 views

Training the generator in a GAN pair with back propagation

For the purposes of this question I am asking about training the generator, assume that training the discriminator is another topic. My understanding of generative adversarial networks is that you ...
2
votes
0answers
27 views

Using two generative adversarial nets to classify articles - what is a good approach?

I'm trying to create a deep learning network to classify news article based on the text and associated image. The idea comes from a novel use of GANs to classify based on generated data. My approach ...
1
vote
0answers
14 views

Hyperparameters for Reproducing the Results of IRGAN on MovieLens 1M

I am trying to reproduce results reported for IRGAN (information retrieval GAN) on the MovieLens 1M dataset. The results I want to reproduce and their sources are listed in the table below. Model ...
1
vote
0answers
34 views

Which approach best suits vector encodings?

I want to build a model that when given two vectors, outputs the probability of one vector being the encoded form of the other. I have 2 strategies for this: (Dataset available) I can directly feed ...
1
vote
0answers
35 views

SAGAN - is there a mistake in the original paper?

in the original paper the following scheme of the self-attention appears: https://arxiv.org/pdf/1805.08318.pdf In a later overview: https://arxiv.org/pdf/1906.01529.pdf this scheme appears: ...
1
vote
1answer
41 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 ...
1
vote
0answers
18 views

Why does the relativistic discriminator increase the probability that generated data are real and decrease the probability that real data are real?

I was reading the ESRGAN whitepaper, where I came across this line: Relativistic discriminator [2] is developed not only to increase the probability that generated data are real but also to ...
1
vote
0answers
77 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 ...
1
vote
0answers
19 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. ...
1
vote
1answer
71 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
30 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
97 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 ...
1
vote
0answers
29 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 ...
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 ...
1
vote
1answer
34 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, ...
1
vote
0answers
63 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 ...
1
vote
0answers
32 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
31 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
79 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&...
1
vote
0answers
44 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 ...
1
vote
0answers
46 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
61 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
32 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 ...
1
vote
0answers
77 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
54 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: [...
1
vote
0answers
14 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
21 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 ...
1
vote
0answers
46 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
35 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-...