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
20
votes
3answers
25k views

How can we process the data from both the true distribution and the generator?

I'm struggling to understand the GAN loss function as provided in Understanding Generative Adversarial Networks (a blog post written by Daniel Seita). In the standard cross-entropy loss, we have an ...
13
votes
2answers
2k views

How are generative adversarial networks trained?

I am reading about generative adversarial networks (GANs) and I have some doubts regarding it. So far, I understand that in a GAN there are two different types of neural networks: one is generative ($...
11
votes
2answers
6k views

Why is it called Latent Vector?

I just learned about GAN and I'm a little bit confused about the naming of Latent Vector. First, In my understanding, a definition of a latent variable is a random variable that can't be measured ...
11
votes
1answer
1k views

Understanding notation of Goodfellow's GAN objective function

What is the meaning of $V(D,G)$? How do we get these expectation parts? I was trying to understand it following this article: Understanding Generative Adversarial Networks (D.Seita), but, after many ...
10
votes
1answer
224 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. ...
9
votes
3answers
2k views

Do GANs come under supervised learning or unsupervised learning?

Do GANs come under supervised learning or unsupervised learning? My guess is that they come under supervised learning, as we have labeled dataset of images, but I am not sure as there might be other ...
7
votes
1answer
189 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 ...
7
votes
1answer
873 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 ...
7
votes
0answers
73 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 ...
6
votes
2answers
156 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 ...
5
votes
2answers
6k views

Why are Variational autoencoder's output is blurred while GANs output is crisp and has sharp edges?

I observed in several papers that the Variational autoencoder's output is blurred while GANs output is crisp and has sharp edges. Can someone please give some intuition why that is the case? I did ...
5
votes
1answer
141 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 ...
5
votes
1answer
115 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?
5
votes
1answer
143 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 ...
5
votes
1answer
355 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-...
5
votes
3answers
136 views

What is an “adversarial attack”

I'm reading this really interesting article CycleGAN, a Master of Steganography and I understand everything up until this paragraph: we may view the CycleGAN training procedure as continually ...
5
votes
1answer
175 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
0answers
134 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
1answer
66 views

GAN Generator Output w/ Periodic Noise

I am training a Semi-Supervised GAN, using multivariate time-series with window of shape (180*80) with the generator and discriminator architecture below. My data is scaled using Robust Scaler, so I ...
4
votes
1answer
50 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(...
4
votes
2answers
1k views

Using GAN's to generate dataset for CNN training

I'm doing bachaleor thesis on traffic sign detection using single shot detector called YOLO. These single shot detectors can perform detection of objects in image and so they have specific way of ...
4
votes
1answer
362 views

What kind of algorithm is used by StackGAN to generate realistic images from text?

What kind of algorithm is used by StackGAN to generate realistic images from text? How does StackGAN work?
4
votes
1answer
191 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?...
4
votes
1answer
92 views

How can I use Generative Adversarial Networks to solve the imbalanced class problem?

Problem setting We have to do a binary classification of data given a training dataset $D$, where most items belong to class $A$ and some items belong to class $B$, so the classes are heavily ...
4
votes
1answer
3k views

Are deep learning models suitable for training with sparse data?

I am training a generative adversarial network (GAN) to generate images given edge histogram descriptor (EHD) features of the image. The EHD features are themselves sparse (meaning they contain a lot ...
4
votes
1answer
178 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 ...
4
votes
0answers
38 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
2answers
146 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
2answers
535 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 ...
3
votes
1answer
3k views

Why doesn't VAE suffer mode collapse?

Mode collapse is a common problem faced by GANs. I am curious why doesn't VAE suffer mode collapse?
3
votes
1answer
183 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 ...
3
votes
1answer
149 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?
3
votes
1answer
1k 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 ...
3
votes
3answers
726 views

Why use the output of the generator to train the discriminator in a GAN?

I've been doing some reading about GANs, and although I've seen several excellent examples of implementations, the descriptions of why those patterns were chosen isn't clear to me in many cases. At a ...
3
votes
1answer
75 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 ...
3
votes
1answer
58 views

Why do we sample vectors from a standard normal distribution for the generator?

I am new to GANs. I noticed that everybody generates a random vector (usually 100 dimensional) from a standard normal distribution $N(0, 1)$. My question is: why? Why don't they sample these vectors ...
3
votes
0answers
38 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
533 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
36 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. ...
3
votes
2answers
377 views

How to use a Generative Adversarial Network to generate images for developmental analysis?

I want to generate images of childrens' drawings consistent with the developmental state of children of a given age. The training data set will include drawings made by real children in a school ...
2
votes
2answers
113 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
2answers
105 views

What are the possible social consequences of training neural networks with artificially generated data?

Machine learning models and, in particular, neural networks are trained with data often collected from the real world, such as images of real people. Meanwhile, neural networks (such as GANs) are also ...
2
votes
1answer
43 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 ...
2
votes
1answer
64 views

In style transfer, why does the comparison between channels give a good sense of style?

I have been learning about Style Transfer recently. Style is defined as The correlation of activations between channels. I can't seem to understand why that would be true. Intuitively, style seems ...
2
votes
1answer
54 views

Is it possible to use an internal layer's outputs in a loss function?

For a network of the form: Input(10) Dense(200) Dense(100+10) Dense(20) Output() Those +10 outputs are what I want to add to ...
2
votes
1answer
49 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 ...
2
votes
1answer
60 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 ...
2
votes
2answers
78 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 ...