Deep Deterministic Uncertainty for Semantic Segmentation [article]

Jishnu Mukhoti, Joost van Amersfoort, Philip H.S. Torr, Yarin Gal
2021 arXiv   pre-print
We extend Deep Deterministic Uncertainty (DDU), a method for uncertainty estimation using feature space densities, to semantic segmentation. DDU enables quantifying and disentangling epistemic and aleatoric uncertainty in a single forward pass through the model. We study the similarity of feature representations of pixels at different locations for the same class and conclude that it is feasible to apply DDU location independently, which leads to a significant reduction in memory consumption
more » ... pared to pixel dependent DDU. Using the DeepLab-v3+ architecture on Pascal VOC 2012, we show that DDU improves upon MC Dropout and Deep Ensembles while being significantly faster to compute.
arXiv:2111.00079v1 fatcat:xal74vuiwfdongiio2d3dy2p3e