All Questions
47 questions
2
votes
0
answers
174
views
Maximum Mean Discrepancy (MMD) implementation as a metric to measure GAN performance [closed]
I am trying to evaluate the performance of the GAN model, I have trained. I found that there exist two major choices FID (Fréchet inception distance) and MMD (Maximum Mean Discrepancy) for comparing ...
- 21
0
votes
1
answer
89
views
In factor VAE, do you freeze the discriminator weights during the back propagation step for the FVAE loss?
In factor vae, Disentangling by Factorising, there are two losses that are minimized. One is the VAE loss (eq. 2 in the paper) that includes (1) reconstruction loss, (2) KL divergence and (3) Total ...
- 33
0
votes
1
answer
114
views
VAE active units
According to Burda et al (2015) number of active units is computed as:
$ Cov_x(E_{z \sim q_\phi(z|x)}) > \delta $
for some particular delta. In the paper it is set to 0.02 empirically. But this ...
2
votes
1
answer
1k
views
How to generate new data with a VAE?
I have built the following function which takes as input some data and runs a VAE on them:
...
- 531
4
votes
1
answer
1k
views
How to rewrite DreamBooth loss in terms of $\epsilon$-prediction?
I'm trying to make the loss used in DreamBooth paper explicit, writing it in terms of the noise, as it is commonly written in the original diffusion article [1], instead of the image reconstruction ...
- 505
3
votes
2
answers
2k
views
Can the dimension of the latent space in VAEs, be larger than the dimension of the data?
I am experimenting with VAEs. There, there is a parameter that you need pass when you create the NN, which is the dimension of the latent space.
In the typical ...
- 531
2
votes
1
answer
967
views
Initialization of GAN discriminator
The question is pretty straightforward: how are GAN and WGAN discriminators typically initialized?
I couldn't find much info on this. E.x. for GANs, I imagine you would theoretically want the ...
- 143
2
votes
0
answers
105
views
Restricted Boltzmann Machine: W matrix visualization results after training MNIST images and Pseudo-log-likelihood
I am implementing RBM from scratch using Tensorflow and after training my RBM on the MNIST dataset for 200 epochs using Persistent CD with two steps of contrastive divergence, I learn the weights W ...
- 21
1
vote
0
answers
220
views
Synthetic data generation - GANs vs Simulator?
For synthetic data generation, does the GAN perform better than a simulator? If so, what are the limitations of the simulator?
If we consider Conditional GANs, we could generate data based on the ...
- 111
0
votes
0
answers
418
views
I need help understanding the meaning of the loss values of a WGAN with Gradient Penalty
I am currently working on training a Auxiliary Classifier Wasserstein GAN with Gradient Penalty. I based my implementation off of https://keras.io/examples/generative/wgan_gp/ (to which I added the ...
2
votes
1
answer
297
views
Issues with GAN and VAE models
I'm reading this amazing paper on Normalizing Flows https://arxiv.org/pdf/1908.09257.pdf but one sentence kind of bothers me:
GANs and VAEs have demonstrated impressive performance results on
...
3
votes
1
answer
1k
views
How to find bits/dim of a gaussian output distribution?
I have images that are 64x64x3 and 64x64x1 8-bit. I transform those images down to [-1,1]. I now want to find the bits/dim for my VAE log probability. How do I find the bits/dim of the log likelihood? ...
- 65
2
votes
1
answer
480
views
Can PCA generate a new random image?
I read The Batch: GANs newsletter and Goodfellow said:
My colleague Bing Xu modeled face images from the Toronto Face Database, which were only 90 pixels square and grayscale. Because the faces were ...
- 121
3
votes
3
answers
2k
views
In VAE, why use MSE loss between input x and decoded sample x' from latent distribution?
Variational Autoencoders (VAEs) are based on the concept of Variational Inference (VI) and use two Neural Networks similar to Vanilla Autoencoders (AEs) for function approximation. I understood the ...
- 61
3
votes
1
answer
444
views
Can someone explain CAM loss used in U-GAT-IT paper?
I have been reading a recent paper accepted at ICLR, U-GAT-IT, which seems to produce pleasing results in the image-to-image translation tasks. There are four kinds of loss used in this paper: ...
3
votes
1
answer
209
views
Why is using a mixture of logstic distributions makes sense in pixelcnn++?
I went trough the paper and code of the pixelcnn++ model.
From what I understand, they train the network in the following way for predicting the value of a single pixel:
the inputs are the pixel ...
- 273
0
votes
0
answers
116
views
Generating Graphs using a Neural Network
I currently have constructed a Graph Neural Network in PyTorch with graph conv layers I have made. With this, I am able to feed in adjacency and feature matrices and successfully perform node ...
- 176
1
vote
2
answers
40
views
How to extract crucial features to create an image
Imagine, you have a dataset containing pictures of (example only, just to explain the task) cats and dogs. The data set is labeled, so we can train using supervised learning algorithms.
My goal is ...
8
votes
1
answer
204
views
Structure of Generative Adversarial Networks (GAN) for mapping a simulation model
There is a simulation model of a system that I want to map as a neural network to test if a better execution time can be achieved with similar accuracy.
The simulation model receives real-valued ...
- 93
13
votes
1
answer
730
views
How to understand Generative Adversarial Networks Discriminative distribution?
So I am currently studying Generative Adversarial Network and I read the paper by Goodfellow a few times now Generative Adversarial Nets and a few other papers in this field (DCGAN, CycleGAN, pix2pix, ...
- 235
1
vote
0
answers
168
views
Are Flow Based Generative Models Referring to the Invertible Transformations?
So I have been studying generative models for a while now. I know how GANs and VAEs work quite well, but I am quite confused by how Flow Based Generative Models work.
To my understanding, flow based ...
- 23
0
votes
1
answer
91
views
Learning Deep Generative Models of Graphs
I'm reading through Learning Deep Generative Models of Graphs, which is a paper that seems to me propose some sort of variational autoencoder to generate a graph.
At very high level the semantic of ...
- 213
1
vote
2
answers
97
views
Working mechanism of discriminator in text to image synthesis GAN
I have the following architecture of discriminator in text to image synthesis where the image is convolved to lower dimension and concatenated with the text . My question is what is the use of ...
2
votes
1
answer
1k
views
How does one generate (smooth) varying size output signals with Machine Learning?
I am interested in knowing about generative methods that generate signals (e.g. images) of varying sizes. But the size generation being sort of "smooth/continuous". So for example, generating images ...
- 7,074
2
votes
0
answers
54
views
Extracting likelihoods from generative model
I am looking for papers dealing with the extraction of explicit descriptions of probability distributions from a generative model. My use case is the following: I trained a GAN to generate samples ...
- 528
2
votes
0
answers
49
views
How do I check my GAN implementation is correct?
I wrote a GAN implementation and I trained that to produce some sample images after training on a dataset. The images looked visually fine.
Now I want to test my implementation on the CI and make ...
- 121
2
votes
1
answer
2k
views
On evaluating variational autoencoders with prior likelihood and reconstruction error
A common evaluation metric for variational autoencoders (VAEs) is estimating the marginal likelihood of some held-out data, i.e. $p(x)$. This is difficult and often one can only get a lower bound. It'...
- 2,284
5
votes
1
answer
118
views
Convergence to gradient in limit of variance
I came across this equation in the original GAN paper (pg 2 https://papers.nips.cc/paper/5423-generative-adversarial-nets.pdf):
$$\lim_{\sigma \rightarrow 0}
\nabla_{\bf x} \mathbb{E}_{\epsilon \sim \...
- 205
2
votes
0
answers
70
views
Understanding probabilistic inference graphs
I am having trouble understanding inference graphs. In the diagram below I understand the graph on the left (forward graph) where the arrows describe the direction that data flows when training for ...
- 967
2
votes
0
answers
127
views
What is the difference between a conditional model and just having multiple models?
Say I have a labeled dataset that I want to create a generative model for, like a Generative Adversarial Network or a Variational Autoencoder. What do I gain or lose by making my models conditional (i....
1
vote
0
answers
412
views
Which GAN is the best for data augmentation?
I have around 200000 images and I want to augment the data by generating more of them. Images do not have classes, because they are the same object and are used for the task of object detection.
Can I ...
- 123
22
votes
4
answers
8k
views
Likelihood-free inference - what does it mean?
Recently I have become aware of 'likelihood-free' methods being bandied about in literature. However I am not clear on what it means for an inference or optimization method to be likelihood-free.
In ...
- 967
14
votes
3
answers
3k
views
Is the optimization of the Gaussian VAE well-posed?
In a Variational Autoencoder (VAE), given some data $x$ and latent variables $t$ with prior distribution $p(t) = \mathcal{N}(t \mid 0, I)$, the encoder aims to learn a distribution $q_{\phi}(t)$ that ...
- 707
3
votes
0
answers
99
views
Generative Adversarial Network and Variational Autoencoders for Independent Component Analysis?
Background:
I'm working on a model for independent component analysis (ICA) that is based on a methodology similar to GANs and VAEs. What I'm having trouble understanding is how the choice of the loss ...
- 1,368
2
votes
1
answer
1k
views
How sampling and KL loss work in Variational Autoencoders?
I am trying to learn about Variational Autoencoders and found this very informative blog about vae's. I understood most part of vae's but cant understand how sampling and KL loss work in a vae.
This ...
- 2,291
2
votes
1
answer
4k
views
What is minibatch discrimination?
Can someone explain what minibatch discrimination is, in simple terms?
Here is the link to the original paper.
(Minibatch discrimination: Sec 3.2, page 3)
- 171
5
votes
1
answer
7k
views
How to interpret the following GAN training losses?
I am training a GAN using the following loss functions:
...
- 171
1
vote
0
answers
2k
views
GAN losses balance, but quality of generated image still bad
I build a GAN to train on the fashion mnist dataset.
To facilitate the training, I have added gaussian noise with mean 0 and stddev 0.15 on the images. My generator is a 2 layer MLP with sigmoid ...
- 319
16
votes
1
answer
18k
views
Variational Autoencoder − Dimension of the latent space
I've done some experiments to understand the influence of the dimension of the latent space in a VAE, and it seems that the higher the space, the harder it is to generate realistic images. I might ...
- 263
1
vote
1
answer
34
views
Generating Synthetic Food Orders
I have some transactional data for users who have ordered food. However, I am not allowed to share this data but am allowed to augment or generate a synthetic sample and share it. I was thinking about ...
- 51
2
votes
1
answer
1k
views
Some confusion on learning of Generative Adversarial Networks (GANs)
I have some experience with machine learning, but no background in deep learning at all. The idea of a GAN looks so cool, and there are so many sources out there that talks about the idea, but there ...
- 1,579
4
votes
1
answer
1k
views
Generative Adversial Networks: how the generator is trained with the output of discriminator
Recently I have learned about Generative Adversarial Networks.
For training the Generator, I am somehow confused how it learns. Here is an implemenation of GANs:
...
- 395
2
votes
1
answer
7k
views
Regression vs. classification and generative vs. discriminative
I recently touch the idea of Generative adversarial networks, which is a competition between a generative network and a discriminative network.
This idea makes me think of replacing the word "network"...
- 121
5
votes
3
answers
361
views
Tutorial recommendations for understanding GANs
I understand that generative adversarial networks (GANs) can synthetically reconstruct the input using a generator and a discriminator in a zero-sum game. However, I feel that I do not fully ...
3
votes
1
answer
210
views
Boltzmann machines: learning algorithm
I'm trying to study Boltzmann machines, so I don't undestand this recurrent formulation for the training stage of the weights $w$:
$\Delta w_{ij} = E_{data} (v_i h_j ) − E_{model} (v_i h_j )$
all ...
- 747
12
votes
2
answers
7k
views
What does log-likelihood mean in the context of generative models like GANs?
I understand the general notion of likelihood as "probability to generate the data given parameters" (like here). But people use (log-)likelihood as a measure of "goodness" of a generative model.
...
- 223
5
votes
0
answers
379
views
What enforces features diversity in RBM?
I'm working on an implementation of a Restricted Boltzman Machine (RBM). I made some tests on the MNIST dataset trying to learn a representation of the digit 2. My inputs are binary images. My aim is ...
- 213