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
1
vote
0answers
18 views

How do I implement the loss function for untargeted attacks described in “A General Framework for Adversarial Examples with Objectives”?

I am trying to implement the ideas in the paper A General Framework for Adversarial Examples with Objectives. In equation \ref{3}, they define the loss as: $$\text{Loss}_G(Z,D) - \kappa \sum \text{...
1
vote
0answers
35 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
8 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
33 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
25 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
26 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
31 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
29 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
43 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
33 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
0answers
16 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
16 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
71 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 ...
1
vote
0answers
14 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
35 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
34 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 ...
0
votes
2answers
70 views

How can I implement a GAN network for text (review) generation?

How can I implement a GAN network for text (review) generation? Please, can someone guide me to resource (code) to help in text generation?
1
vote
0answers
21 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
2answers
206 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 ...
3
votes
1answer
92 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 ...
0
votes
0answers
28 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 ...
1
vote
0answers
24 views

What is the intuition behind the Label Smoothing?

I was learning about GAN when the term "Label Smoothing" appears. From the video tutorial that I watch, they use the term "label smoothing" to change the binary labels when calculating the loss of ...
2
votes
2answers
90 views

How important is it that the generator of a generative adversarial network doesn't take in information about input classes?

I'm building a generative adversarial network that generates images based on an input image. From the literature I've read on GANs, it seems that the generator takes in a random variable and uses it ...
4
votes
1answer
130 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 ...
1
vote
1answer
42 views

How to get good results with GAN and some thousands of images?

I'm trying to generate images at minimum of size 128 x 128 with a Generative Adversarial Network. I already tried a SAGAN pytorch implementation, but I'm not very happy with results. The images look ...
0
votes
0answers
142 views

1D GAN not converging

I am trying to build a 1D GAN able to produce data similar to the input one, which looks like this: I am using pytorch. This is the code for my Discriminator, which takes as input a 1D vector of size ...
0
votes
1answer
46 views

How to study the correlation between GAN's input vector and output image

A generative adversarial network (GAN) takes a vector of numbers as input and generates an image, based on the input. Each element of the vector causes some feature of the image to change, but the ...
2
votes
2answers
310 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 ...
0
votes
1answer
54 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
2answers
298 views

Can we implement GAN (Generative adversarial neural networks) for classication problem like Fraud detecion?

Problem: Fraud detection Task : classifying transactions as either fraud/ Non-fraud using GAN
5
votes
2answers
399 views

Do GAN's come under Supervised Learning or Unsupervised Learning?

My guess is that they come under supervised learning, as we have labelled dataset of images, but I am not sure as there maybe other aspects in GANs which might come into play in the determination of ...
3
votes
2answers
1k 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 ...
1
vote
1answer
662 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? Some source
4
votes
1answer
45 views

Class Restriction in Generative Adversarial Networks

this is my first post here. Our problem setting: We have to do a binary classification of data given a training-dataset D, where the majority of items belongs to class A and some items belong to ...
1
vote
1answer
39 views

why D(x|y) and not D(x,y) in conditional generative networks

In conditional Generative Adversarial Networks (GAN), https://arxiv.org/pdf/1411.1784.pdf, the loss function is, Discriminator and Generator both takes y, the auxiliary information. I am confused as ...
3
votes
2answers
321 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 ...
4
votes
2answers
576 views

How to go forward with creating an artifically intelligent aimbot for a game like CS:GO

Artificial Intelligence can be realized as a full autonomous or as a semi-autonomous system. A full autonomous system takes the human operator out of the loop, his hands are away from keyboard and he ...
1
vote
0answers
293 views

Why do we need Upsampling and Downsampling in Progressive Growing of Gans

I was working recently on Progressive Growing of GANs (aka PGGANs). I have implemented the whole architecture, but the problem that was ticking my mind is that in simple GANs, like DCGAN, PIX2PIX, we ...
2
votes
0answers
22 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 ...
2
votes
1answer
114 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 ...
27
votes
9answers
5k views

Is artificial intelligence vulnerable to hacking?

The paper The Limitations of Deep Learning in Adversarial Settings explores how neural networks might be corrupted by an attacker who can manipulate the data set that the neural network trains with. ...
16
votes
3answers
21k views

Understanding GAN loss function

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 ...
12
votes
2answers
1k views

How do generative adversarial networks work?

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 ($...