Viet-Anh on Software Logo

What is: StyleALAE?

SourceAdversarial Latent Autoencoders
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

StyleALAE is a type of adversarial latent autoencoder that uses a StyleGAN based generator. For this the latent space W\mathcal{W} plays the same role as the intermediate latent space in StyleGAN. Therefore, the GG network becomes the part of StyleGAN depicted on the right side of the Figure. The left side is a novel architecture that we designed to be the encoder EE. The StyleALAE encoder has Instance Normalization (IN) layers to extract multiscale style information that is combined into a latent code ww via a learnable multilinear map.