Reviews: What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?

The authors restrict their analysis to aleatoric and epistemic uncertainty (leaving out numerical uncertainty). Aleatoric uncertainty includes the uncertainty from statistical noise in data. Epistemic uncertainty is usually another term for ignorance, i.e. things one could in theory know but doesn't know in practice. In this paper however, the authors use epistemic uncertainty as a synonym for model uncertainty (or structural uncertainty, i.e. ignorance over the true physical model which created the data). The paper raises the question how these two sources of uncertainty can be jointly quantified, and when which source of uncertainty is dominant.