Functional Space Variational Inference for Uncertainty Estimation in Computer Aided Diagnosis

Pranav Poduval, Hrushikesh Loya, Amit Sethi

Keywords: Uncertainty estimation, Variational Inference, Calibration, Skin Lesion

TL;DR: Meaningful priors on the functional space rather than the weight space, result in well calibrated uncertainty estimates

Track: short paper

Paper Type: methodological development

Abstract: Deep neural networks have revolutionized medical image analysis and disease diagnosis. Despite their impressive performance, it is difficult to generate well-calibrated probabilistic outputs for such networks, which makes them uninterpretable black boxes. Bayesian neural networks provide a principled approach for modelling uncertainty and increasing patient safety, but they have a large computational overhead and provide limited improvement in calibration. In this work, by taking skin lesion classification as an example task, we show that by shifting Bayesian inference to the functional space we can craft meaningful priors that give better-calibrated uncertainty estimates at a much lower computational cost

Presentation Upload Agreement: I agree that my presentation material (videos and slides) will be made public.