DeepAI AI Chat
Log In Sign Up

Independent Subspace Analysis for Unsupervised Learning of Disentangled Representations

by   Jan Stühmer, et al.

Recently there has been an increased interest in unsupervised learning of disentangled representations using the Variational Autoencoder (VAE) framework. Most of the existing work has focused largely on modifying the variational cost function to achieve this goal. We first show that these modifications, e.g. beta-VAE, simplify the tendency of variational inference to underfit causing pathological over-pruning and over-orthogonalization of learned components. Second we propose a complementary approach: to modify the probabilistic model with a structured latent prior. This prior allows to discover latent variable representations that are structured into a hierarchy of independent vector spaces. The proposed prior has three major advantages: First, in contrast to the standard VAE normal prior the proposed prior is not rotationally invariant. This resolves the problem of unidentifiability of the standard VAE normal prior. Second, we demonstrate that the proposed prior encourages a disentangled latent representation which facilitates learning of disentangled representations. Third, extensive quantitative experiments demonstrate that the prior significantly mitigates the trade-off between reconstruction loss and disentanglement over the state of the art.


page 13

page 15

page 16

page 17

page 18

page 19

page 20

page 21


A Closer Look at Disentangling in β-VAE

In many data analysis tasks, it is beneficial to learn representations w...

Disentangling Representations using Gaussian Processes in Variational Autoencoders for Video Prediction

We introduce MGP-VAE, a variational autoencoder which uses Gaussian proc...

Variational Inference of Disentangled Latent Concepts from Unlabeled Observations

Disentangled representations, where the higher level data generative fac...

Variational AutoEncoder For Regression: Application to Brain Aging Analysis

While unsupervised variational autoencoders (VAE) have become a powerful...

Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations

We would like to learn a representation of the data which decomposes an ...

Disentangling by Factorising

We define and address the problem of unsupervised learning of disentangl...

Gated Variational AutoEncoders: Incorporating Weak Supervision to Encourage Disentanglement

Variational AutoEncoders (VAEs) provide a means to generate representati...