no code implementations • 27 Jun 2022 • Sebastian G. Popescu, David J. Sharp, James H. Cole, Konstantinos Kamnitsas, Ben Glocker
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.
no code implementations • 28 Apr 2021 • Sebastian G. Popescu, David J. Sharp, James H. Cole, Konstantinos Kamnitsas, Ben Glocker
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.