Deep Deterministic Uncertainty for Semantic Segmentation
arXiv:2111.00079
Abstract
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 compared 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.
References in corpus (7)
- Rethinking Atrous Convolution for Semantic Image Segmentation
- What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
- Bayesian Active Learning for Classification and Preference Learning
- Evaluating Bayesian Deep Learning Methods for Semantic Segmentation
- Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness
- Autonomous Driving with Deep Learning: A Survey of State-of-Art Technologies