HIGHLIGHTS
- who: Semi-Supervised Adversarial Variational Autoencoder and collaborators from the (UNIVERSITY) have published the Article: machine learning & knowledge extraction, in the Journal: (JOURNAL)
- what: The authors propose a method to inject an adversarial learning into a VAE to improve its reconstruction and generation performance. The method proposed in this paper, which is presented in Figure 3, consists of separating the learning of the VAE into two successive parts: the learning of the encoder Enc( x ) followed by the learning of the decoder Dec(z). As previously used by Hou , instead of comparing the reconstructed data . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.