Training VAEs Under Structured Residuals

04/03/2018
by   Garoe Dorta, et al.
0

Variational auto-encoders (VAEs) are a popular and powerful deep generative model. Previous works on VAEs have assumed a factorised likelihood model, whereby the output uncertainty of each pixel is assumed to be independent. This approximation is clearly limited as demonstrated by observing a residual image from a VAE reconstruction, which often possess a high level of structure. This paper demonstrates a novel scheme to incorporate a structured Gaussian likelihood prediction network within the VAE that allows the residual correlations to be modelled. Our novel architecture, with minimal increase in complexity, incorporates the covariance matrix prediction within the VAE. We also propose a new mechanism for allowing structured uncertainty on color images. Furthermore, we provide a scheme for effectively training this model, and include some suggestions for improving performance in terms of efficiency or modelling longer range correlations. The advantage of our approach is illustrated on the CelebA face data and the LSUN outdoor churches dataset, with substantial improvements in terms of samples over traditional VAE and better reconstructions.

READ FULL TEXT

page 1

page 7

page 9

page 11

page 12

page 13

page 14

research
02/20/2018

Structured Uncertainty Prediction Networks

This paper is the first work to propose a network to predict a structure...
research
01/17/2019

Hierarchical Representations with Poincaré Variational Auto-Encoders

The Variational Auto-Encoder (VAE) model has become widely popular as a ...
research
05/25/2023

Bi-fidelity Variational Auto-encoder for Uncertainty Quantification

Quantifying the uncertainty of quantities of interest (QoIs) from physic...
research
06/09/2020

Novelty Detection via Robust Variational Autoencoding

We propose a new method for novelty detection that can tolerate nontrivi...
research
06/17/2020

Longitudinal Variational Autoencoder

Longitudinal datasets measured repeatedly over time from individual subj...
research
10/27/2022

Model Order Selection with Variational Autoencoding

Classical methods for model order selection often fail in scenarios with...

Please sign up or login with your details

Forgot password? Click here to reset