Should VAEs be even used for non-generative tasks? If I were to use both models for embedding images, how would the embedding space differ on a structural level?


For the vanilla autoencoder the structure is like this:

enter image description here

It can be treated as a nonlinear extension of PCA, while for the variational autoencoder a mean and a standard deviation is added as a layer for each hidden variable in the middle layer:

enter image description here

For the detailed difference please refer to this answer.

Intuitively Understanding Variational Autoencoders

  • $\begingroup$ Sorry, but this only states what they are. I'm asking for how they differ when it comes to non-generative tasks such as embeddings. $\endgroup$ – Daniel Aug 11 at 22:43
  • 1
    $\begingroup$ @Daniel OK. I will update that later. $\endgroup$ – Lerner Zhang Aug 11 at 22:47

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.