1. Distributional Gaussian Processes Layers for Out-of-Distribution Detection
- Author
-
Popescu, Sebastian G., Sharp, David J., Cole, James H., Kamnitsas, Konstantinos, and Glocker, Ben
- Subjects
Computer Science - Computer Vision and Pattern Recognition ,Computer Science - Machine Learning ,Statistics - Machine Learning - 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. To facilitate future work our code is publicly available., Comment: Published in Journal of Machine Learning for Biomedical Imaging: Special Issue: Information Processing in Medical Imaging (IPMI) 2021
- Published
- 2022