no code implementations • 21 Mar 2021 • Renfei Tu, Yang Liu, Yongzeng Xue, Cheng Wang, Maozu Guo
Being one of the most popular generative framework, variational autoencoders(VAE) are known to suffer from a phenomenon termed posterior collapse, i. e. the latent variational distributions collapse to the prior, especially when a strong decoder network is used.