DeepAI AI Chat
Log In Sign Up

Deep Deterministic Uncertainty for Semantic Segmentation

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.


page 2

page 4


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

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

Quantifying Model Uncertainty for Semantic Segmentation using Operators in the RKHS

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

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

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

On the Practicality of Deterministic Epistemic Uncertainty

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

Semantic Segmentation with Labeling Uncertainty and Class Imbalance

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

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

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

Training, Architecture, and Prior for Deterministic Uncertainty Methods

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