Distributional Gaussian Processes Layers for Out-of-Distribution Detection
Sebastian G. Popescu1, David J. Sharp1, James H. Cole2, Konstantinos Kamnitsas1, Ben Glocker1
1: Imperial College London, 2: University College London
IPMI 2021 special issue
Publication date: 2022/06/29
Abstract
Machine learning models deployed on medical imaging tasks must be equipped with out-of-distribution detection capabilities in order to avoid erroneous predictions. It is unsure whether out-of-distribution detection models reliant on deep neural networks are suitable for detecting domain shifts in medical imaging. Gaussian Processes can reliably separate in-distribution data points from out-of-distribution data points via their mathematical construction. Hence, we propose a parameter efficient Bayesian layer for hierarchical convolutional Gaussian Processes that incorporates Gaussian Processes operating in Wasserstein-2 space to reliably propagate uncertainty. This directly replaces convolving Gaussian Processes with a distance-preserving affine operator on distributions. Our experiments on brain tissue-segmentation show that the resulting architecture approaches the performance of well-established deterministic segmentation algorithms (U-Net), which has not been achieved with previous hierarchical Gaussian Processes. Moreover, by applying the same segmentation model to out-of-distribution data (i.e., images with pathology such as brain tumors), we show that our uncertainty estimates result in out-of-distribution detection that outperforms the capabilities of previous Bayesian networks and reconstruction-based approaches that learn normative distributions.
Keywords
gaussian processes · image segmentation · out-of-distribution detection
Bibtex
@article{melba:2022:009:popescu,
title = "Distributional Gaussian Processes Layers for Out-of-Distribution Detection",
author = "Popescu, Sebastian G. and Sharp, David J. and Cole, James H. and Kamnitsas, Konstantinos and Glocker, Ben",
journal = "Machine Learning for Biomedical Imaging",
volume = "1",
issue = "IPMI 2021 special issue",
year = "2022",
pages = "1--64",
issn = "2766-905X",
url = "https://melba-journal.org/2022:009"
}
RIS
TY - JOUR
AU - Popescu, Sebastian G.
AU - Sharp, David J.
AU - Cole, James H.
AU - Kamnitsas, Konstantinos
AU - Glocker, Ben
PY - 2022
TI - Distributional Gaussian Processes Layers for Out-of-Distribution Detection
T2 - Machine Learning for Biomedical Imaging
VL - 1
IS - IPMI 2021 special issue
SP - 1
EP - 64
SN - 2766-905X
UR - https://melba-journal.org/2022:009
ER -
