Training VAEs Under Structured Residuals
arXiv:1804.01050
Abstract
Variational auto-encoders (VAEs) are a popular and powerful deep generative model. Previous works on VAEs have assumed a factorized 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 modeled. 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 modeling longer range correlations.
arXiv commentSimplified training methodology, added more results
References in corpus (8)
- Auto-Encoding Variational Bayes
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- Pixel Recurrent Neural Networks
- LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
- BEGAN: Boundary Equilibrium Generative Adversarial Networks
- Adversarial Feature Learning