VAE-GANs for Probabilistic Compressive Image Recovery: Uncertainty Analysis

01/31/2019
by   Vineet Edupuganti, et al.
12

Recovering high-quality images from limited sensory data is a challenging computer vision problem that has received significant attention in recent years. In particular, solutions based on deep learning, ranging from autoencoders to generative models, have been especially effective. However, comparatively little work has centered on the robustness of such reconstructions in terms of the generation of realistic image artifacts (known as hallucinations) and quantifying uncertainty. In this work, we develop experimental methods to address these concerns, utilizing a variational autoencoder-based generative adversarial network (VAE-GAN) as a probabilistic image recovery algorithm. We evaluate the model's output distribution statistically by exploring the variance, bias, and error associated with generated reconstructions. Furthermore, we perform eigen analysis by examining the Jacobians of outputs with respect to the aliased inputs to more accurately determine which input components can be responsible for deteriorated output quality. Experiments were carried out using a dataset of Knee MRI images, and our results indicate factors such as sampling rate, acquisition model, and loss function impact the model's robustness. We also conclude that a wise choice of hyperparameters can lead to the robust recovery of MRI images.

READ FULL TEXT

page 5

page 6

page 7

page 8

research
12/19/2018

An Empirical Study of Generative Models with Encoders

Generative adversarial networks (GANs) are capable of producing high qua...
research
02/06/2020

Unbalanced GANs: Pre-training the Generator of Generative Adversarial Network using Variational Autoencoder

We propose Unbalanced GANs, which pre-trains the generator of the genera...
research
06/14/2019

Multi-Adversarial Variational Autoencoder Networks

The unsupervised training of GANs and VAEs has enabled them to generate ...
research
10/17/2020

CQ-VAE: Coordinate Quantized VAE for Uncertainty Estimation with Application to Disk Shape Analysis from Lumbar Spine MRI Images

Ambiguity is inevitable in medical images, which often results in differ...
research
06/25/2022

Sequential image recovery using joint hierarchical Bayesian learning

Recovering temporal image sequences (videos) based on indirect, noisy, o...
research
09/27/2021

DOODLER: Determining Out-Of-Distribution Likelihood from Encoder Reconstructions

Deep Learning models possess two key traits that, in combination, make t...

Please sign up or login with your details

Forgot password? Click here to reset