Deep Deterministic Uncertainty for Semantic Segmentation

2021/10/29 by Jishnu Mukhoti, Mukhoti, Jishnu, Joost van Amersfoort +5 · 2 citations
Computer Science · #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #cs.CV #cs.LG

paper · pdf · doi:10.48550/arxiv.2111.00079

arxiv created 2021/10/29 · openalex publication_date 2021/10/29 · arxiv updated 2021/11/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• The Pascal Visual Object Classes (VOC) Challenge
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Evaluating Bayesian Deep Learning Methods for Semantic Segmentation
• Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• Deep High-Resolution Representation Learning for Visual Recognition
• Autonomous Driving with Deep Learning: A Survey of State-of-Art Technologies

Cited by

• Uncertainty Estimation by Flexible Evidential Deep Learning
• Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information Theory

Related

• On the Practicality of Deterministic Epistemic Uncertainty
• Latent Discriminant deterministic Uncertainty
• Instance-wise Uncertainty for Class Imbalance in Semantic Segmentation
• A Comparative Study on Multi-task Uncertainty Quantification in Semantic Segmentation and Monocular Depth Estimation
• Discriminant Distance-Aware Representation on Deterministic Uncertainty Quantification Methods