2
$\begingroup$

It is well known that variational autoencoders tend to create blurry reconstructions. I want to use the latent variables as image representations, and after training the autoencoder I would like to do transfer learning and use the output of the bottleneck as an input to a binary classifier. I believe the classification task depends on the fine details (high-frequency components) that are lost in the blurry reconstructions. Can I still expect the latent variables to perform well in the classification task?

$\endgroup$
2
  • $\begingroup$ By output of bottleneck you mean the latent features (which are penalized to be normally distributed) or output of some decoding layer? $\endgroup$ Jun 25, 2018 at 7:34
  • $\begingroup$ @JakubBartczuk I mean the latent features which are penalized to be normally distributed $\endgroup$
    – elliotp
    Jun 25, 2018 at 7:36

1 Answer 1

1
$\begingroup$

I don't think anything can be said without trying the experiment. On the one hand, if your conjecture is correct and the high-frequency components are important, then I don't see how an auto-encoder that discards the high-frequency components could succeed. On the other hand, your conjecture could be incorrect, and the model could be adequate.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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