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

@inproceedings{Popescu:2021:10.1007/978-3-030-78191-0_32,
author = {Popescu, SG and Sharp, DJ and Cole, JH and Kamnitsas, K and Glocker, B},
doi = {10.1007/978-3-030-78191-0_32},
publisher = {arXiv},
title = {Distributional gaussian process layers for outlier detection in imagesegmentation},
url = {http://dx.doi.org/10.1007/978-3-030-78191-0_32},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - 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 never been achievedwith previous 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.
AU  - Popescu,SG
AU  - Sharp,DJ
AU  - Cole,JH
AU  - Kamnitsas,K
AU  - Glocker,B
DO  - 10.1007/978-3-030-78191-0_32
PB  - arXiv
PY  - 2021///
TI  - Distributional gaussian process layers for outlier detection in imagesegmentation
UR  - http://dx.doi.org/10.1007/978-3-030-78191-0_32
UR  - http://arxiv.org/abs/2104.13756v1
UR  - https://link.springer.com/chapter/10.1007/978-3-030-78191-0_32
UR  - http://hdl.handle.net/10044/1/88531
ER  -
Download