Options
Robust and Uncertainty-Aware VAE (RU-VAE) for One-Class Classification
Journal
Proceedings - International Symposium on Biomedical Imaging
ISSN
19457928
Date Issued
2022-01-01
Author(s)
Sharma, Renuka
Awate, Suyash P.
Abstract
One-class classification (OCC) methods for abnormality detection learn either a generative model of the inlier class (e.g., using variants of kernel principal component analysis) or a decision boundary to encapsulate the inlier class (e.g., using one-class variants of the support vector machine). Recent methods use deep-neural-network models to learn (for the inlier class) either latent-space distributions or autoencoders, but not both. OCC learning typically relies solely on inlier-class data, but some recent semi-supervised versions also leverage some outlier-class training data. We propose a robust and uncertainty-aware variational framework for OCC, leveraging data-adaptive generalized-Gaussian (GG) models leading to distribution modeling in both latent space and image space. We propose a reparameterization for samples from the latent-space GG to enable backpropagation. Results on publicly available real-world datasets show the benefits of our method over others.
Volume
2022-March
Subjects