REVIEW 2 cited by
Deep Deterministic Uncertainty for Semantic Segmentation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Deep Deterministic Uncertainty for Semantic Segmentation
read the original 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.
Forward citations
Cited by 2 Pith papers
-
SegWithU: Uncertainty as Perturbation Energy for Single-Forward-Pass Risk-Aware Medical Image Segmentation
SegWithU treats uncertainty as perturbation energy via rank-1 probes in a post-hoc head for efficient single-pass risk-aware medical image segmentation, outperforming other single-forward-pass methods on ACDC, BraTS20...
-
Uncertainty in Real-Time Semantic Segmentation on Embedded Systems
Combines pre-trained features, Bayesian regression, and moment propagation to enable real-time epistemic uncertainty for semantic segmentation on embedded systems while preserving accuracy.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.