Imperial College London
Portrait Picture

ProfessorDavidSharp

Faculty of Medicine, Department of Brain Sciences

Professor of Neurology
 
 
 
//

Contact

 

+44 (0)20 7594 7991david.sharp Website

 
 
//

Location

 

UREN.927Sir Michael Uren HubWhite City Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Popescu:2022,
author = {Popescu, SG and Sharp, DJ and Cole, JH and Kamnitsas, K and Glocker, B},
journal = {Journal of Machine Learning for Biomedical Imaging},
title = {Distributional Gaussian Processes Layers for Out-of-Distribution  Detection},
url = {http://arxiv.org/abs/2206.13346v1},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Machine learning models deployed on medical imaging tasks must be equippedwith out-of-distribution detection capabilities in order to avoid erroneouspredictions. It is unsure whether out-of-distribution detection models relianton deep neural networks are suitable for detecting domain shifts in medicalimaging. Gaussian Processes can reliably separate in-distribution data pointsfrom out-of-distribution data points via their mathematical construction.Hence, we propose a parameter efficient Bayesian layer for hierarchicalconvolutional Gaussian Processes that incorporates Gaussian Processes operatingin Wasserstein-2 space to reliably propagate uncertainty. This directlyreplaces convolving Gaussian Processes with a distance-preserving affineoperator on distributions. Our experiments on brain tissue-segmentation showthat the resulting architecture approaches the performance of well-establisheddeterministic segmentation algorithms (U-Net), which has not been achieved withprevious hierarchical Gaussian Processes. Moreover, by applying the samesegmentation model to out-of-distribution data (i.e., images with pathologysuch as brain tumors), we show that our uncertainty estimates result inout-of-distribution detection that outperforms the capabilities of previousBayesian networks and reconstruction-based approaches that learn normativedistributions. To facilitate future work our code is publicly available.
AU  - Popescu,SG
AU  - Sharp,DJ
AU  - Cole,JH
AU  - Kamnitsas,K
AU  - Glocker,B
PY  - 2022///
TI  - Distributional Gaussian Processes Layers for Out-of-Distribution  Detection
T2  - Journal of Machine Learning for Biomedical Imaging
UR  - http://arxiv.org/abs/2206.13346v1
UR  - http://hdl.handle.net/10044/1/98116
ER  -
Download