iVAE-GAN: Identifiable VAE-GAN Models for Latent Representation Learning

iVAE-GAN: Identifiable VAE-GAN Models for Latent Representation Learning

Remarkable progress has been made within nonlinear Independent Component Analysis (ICA) and identifiable deep latent variable models. Formally, the latest nonlinear ICA theory enables us to recover the true latent variables up to a linear transformation by leveraging unsupervised deep learning. This...

Full description

Bibliographic Details
Main Authors: Bjorn Uttrup Dideriksen, Kristoffer Derosche, Zheng-Hua Tan
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Identifiability
VAE-GAN
deep learning
latent representation learning
Online Access:https://ieeexplore.ieee.org/document/9766338/

Internet

https://ieeexplore.ieee.org/document/9766338/

Similar Items