Can someone explain the difference? I'm assuming the difference is just that the neural nets representing the encoder and decoder are trained in a semi-supervised manner in semi-supervised VAE, which in conditional the approximation to the posterior and the posterior's distributions are conditioned on some labels? So, I'm guessing that semi-supervised VAE affects the loss evaluation, whereas, in conditional VAEs, the inference network is conditioned on another label as well?


Your Answer

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

Browse other questions tagged or ask your own question.