DeepAI AI Chat

Deep Deterministic Uncertainty for Semantic Segmentation

10/29/2021

∙

by Jishnu Mukhoti, et al.

∙

∙

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.

Jishnu Mukhoti
9 publications
Joost van Amersfoort
13 publications
Philip H. S. Torr
173 publications
Yarin Gal
126 publications

page 2

page 4

∙ 07/03/2020

Evaluating Uncertainty Estimation Methods on 3D Semantic Segmentation of Point Clouds

Deep learning models are extensively used in various safety critical app...

0 Swaroop Bhandary K, et al. ∙

∙ 11/03/2022

Quantifying Model Uncertainty for Semantic Segmentation using Operators in the RKHS

Deep learning models for semantic segmentation are prone to poor perform...

0 Rishabh Singh, et al. ∙

∙ 03/15/2017

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

There are two major types of uncertainty one can model. Aleatoric uncert...

0 Alex Kendall, et al. ∙

∙ 07/01/2021

On the Practicality of Deterministic Epistemic Uncertainty

A set of novel approaches for estimating epistemic uncertainty in deep n...

4 Janis Postels, et al. ∙

∙ 02/08/2021

Semantic Segmentation with Labeling Uncertainty and Class Imbalance

Recently, methods based on Convolutional Neural Networks (CNN) achieved ...

11 Patrik Olã Bressan, et al. ∙

∙ 03/16/2022

Layer Ensembles: A Single-Pass Uncertainty Estimation in Deep Learning for Segmentation

Uncertainty estimation in deep learning has become a leading research fi...

0 Kaisar Kushibar, et al. ∙

∙ 03/10/2023

Training, Architecture, and Prior for Deterministic Uncertainty Methods

Accurate and efficient uncertainty estimation is crucial to build reliab...

0 Bertrand Charpentier, et al. ∙