Questions tagged [vae]
The vae tag has no summary.
36 questions
0 votes
0 answers
36 views
Can I use the euclidean distance between latent feature vectors obtained from a VAE as a similarity measure for my image dataset?
I have a dataset of human vocalisations during development, separated into syllables. I am using a VAE and I obtain a feature vector for each datapoint from the latent space. Does it make sense to use ...
1 vote
1 answer
39 views
Reduce mode searching behaviour of VAE
I'm applying VAEs to sections genomic data (haplotypic vcf format, so binary variables), with one model being trained on each section. They each have different layer sizes and weights to better fit ...
- 121
1 vote
1 answer
105 views
Not understanding how to eval a VAE model?
As I understanding the VAE, it's a model to get the P(x) of x(final job like image generation). When i train it, It input x from dataset to get mu and var from encoder, and to get a sample z from mu ...
- 13
1 vote
1 answer
862 views
How does a VQ-VAE produce new images?
I'm implementing a VQ-VAE for a LDM for biological time series data. I trained the VQ-VAE, and reconstructions works somewhat reasonable, but I have an understanding problem with how a VQ-VAE works. ...
- 21
0 votes
1 answer
165 views
What neural network architecture would help me model a spectrogram?
I'm really a novice working with these technologies and I'm struggling to design a neural network that is powerful enough to model a spectrogram. For a personal project, I'm working on a spectrogram ...
- 3
4 votes
2 answers
947 views
How does variational autoencoders actually work in comparison to GAN?
I want to know about how variational autoencoders work. I am currently working in a company and we want to incorporate variational autoencoders for creating synthetic data. I have questions regarding ...
- 57
0 votes
1 answer
582 views
What is the dataset during testing a Variational auto-encoder?
I am getting confused in the testing dataset of a VAE. After training the VAE, what should be the testing data-set of the VAE? I understand that during testing the VAE only has the decoder part. Hence,...
- 103
1 vote
1 answer
132 views
Does minimizing kl divergence (i.e. keep approximate posterior close to prior) contradict the goal of avoiding posterior collapse?
Posterior collapse means the variational distribution collapse towards the prior: $\exists i: s.t. \forall x: q_{\phi}(z_i|x) \approx p(z_i)$. $z$ becomes independent of $x$. We would like to avoid it ...
- 21
0 votes
0 answers
101 views
Sigmoid Activation Function (Output layer) Alternative
I have a Convolutional-VAE architecture where the target images are in the range [0, 1], their pixel values. To synthesize/reconstruct images in this scale, I am using a sigmoid activation function in ...
- 121
1 vote
0 answers
24 views
Why only discrete labels are used for (semi-)supervised VAEs?
I've noticed all semi-supervised VAEs assume discrete (categorical) labels to encourage disentangled representation learning in VAEs. e.g., Kingma, Durk P., et al. "Semi-supervised learning with ...
1 vote
1 answer
3k views
KL divergence loss first decreases and then increases in VAE training
I am training a VAE on CelebA HQ (resized to 256x256). The training is going well, the reconstruction loss is decreasing and reconstructions are also meaningful. But, the problem is with KL divergence ...
0 votes
1 answer
140 views
Generate new distribution from auto-encoder /variational autoencoder
I know that autoencoders can be used to generate new data. From what I could understand.. The autoencoder uses the original distribution X to learn a random gaussian distribution described by mean and ...
1 vote
0 answers
99 views
How should I think when I want to compare mu and sigma for different images in VAE?
I'm searching for a way to compare mu and sigma values of the encoder network's output of variational autoencoders. In detail, imagine I trained my VAE on the MNIST digits dataset using the official ...
- 11
1 vote
0 answers
130 views
What does it means (concretly) that a VAE encode inputs as distribution?
From this post we can read that VAEs encode inputs as distributions instead of simple points ? What does it mean concretely ? If the encoder consists of the weights between the input image and the ...
- 111
1 vote
1 answer
289 views
Latent variable graph in Variational Autoencoder
I followed this Keras documentation guide about Auto Encoders. At the end of the documentation there is the graph of the latent variable z: But I can not understand and how to interpret the plot, ...
