Demystifying Inductive Biases for (Beta-)VAE Based Architectures
Dominik Zietlow 1 Michal Rolnek 1 Georg Martius 1
Abstract strates both high semantic quality as well as good perfor-
The performance of β-Variational-Autoencoders mance in terms of disentanglement. Until today, derivates of
(β-VAEs) and their variants on learning seman- VAEs (Higgins et al., 2017; Kim & Mnih, 2018a; Chen et al.,
tically meaningful, disentangled ...


雷达卡




京公网安备 11010802022788号







