Deep Uncertainty

Deep uncertainty focuses on quantifying the reliability of predictions made by deep neural networks, aiming to improve the trustworthiness and interpretability of these models. Current research emphasizes developing and comparing methods for estimating both aleatoric (data-inherent) and epistemic (model-related) uncertainty, often employing techniques like deep ensembles, Monte Carlo dropout, and variational inference within various architectures including implicit neural representations and normalizing flows. This work is crucial for deploying deep learning models in high-stakes applications like medical image analysis, autonomous driving, and scientific visualization, where understanding prediction uncertainty is paramount for safe and reliable decision-making.

Papers

September 5, 2024

Improving Uncertainty-Error Correspondence in Deep Bayesian Medical Image Segmentation
Prerak Mody, Nicolas F. Chaves-de-Plaza, Chinmay Rao, Eleftheria Astrenidou, Mischa de Ridder, Nienke Hoekstra, Klaus Hildebrandt, Marius Staring
Bayesian Uncertainty Structural Uncertainty Deep Uncertainty Voxel Scale Uncertainty

August 12, 2024

Uncertainty-Informed Volume Visualization using Implicit Neural Representation
Shanu Saklani, Chitwan Goel, Shrey Bansal, Zhe Wang, Soumya Dutta, Tushar M. Athawale, David Pugmire, Christopher R. Johnson
Implicit Neural Representation Uncertainty Visualization Deep Uncertainty Volume Visualization

July 23, 2024

Uncertainty-Aware Deep Neural Representations for Visual Analysis of Vector Field Data
Atul Kumar, Siddharth Garg, Soumya Dutta
Visual Data Uncertainty Visualization Deep Uncertainty Uncertainty Aware Model

March 12, 2024

Uncertainty Quantification with Deep Ensembles for 6D Object Pose Estimation
Kira Wursthorn, Markus Hillemann, Markus Ulrich
Uncertainty Quantification Deep Ensemble 6D Object 6D Object Pose Estimation Pose Estimate 6D Object Pose Deep Uncertainty

November 1, 2023

Uncertainty quantification and out-of-distribution detection using surjective normalizing flows
Simon Dirmeier, Ye Hong, Yanan Xin, Fernando Perez-Cruz
Uncertainty Quantification Distribution Detection Normalizing Flow Aleatoric Uncertainty Distribution Datasets Deep Uncertainty Conditional F\"ollmer Flow

August 1, 2023

Dynamic ensemble selection based on Deep Neural Network Uncertainty Estimation for Adversarial Robustness
Ruoxi Qin, Linyuan Wang, Xuehui Du, Xingyuan Chen, Bin Yan
Adversarial Attack Adversarial Robustness Robust Recognition Robust Ensemble Ensemble Selection Deep Uncertainty

March 6, 2023

Evaluating the Fairness of Deep Learning Uncertainty Estimates in Medical Image Analysis
Raghav Mehta, Changjian Shui, Tal Arbel
Deep Learning Procedural Fairness Medical Image Analysis Brain Tumor Segmentation Model Fairness Medical Image Analysis Task Deep Uncertainty

October 2, 2022

Uncertainty estimations methods for a deep learning model to aid in clinical decision-making -- a clinician's perspective
Michael Dohopolski, Kai Wang, Biling Wang, Ti Bai, Dan Nguyen, David Sher, Steve Jiang, Jing Wang
Deep Learning Model Visual Perspective Uncertainty Estimation Method Uncertainty Prediction Clinical Decision Estimation Method Reliable Prediction Deep Uncertainty

September 17, 2022

Linking Neural Collapse and L2 Normalization with Improved Out-of-Distribution Detection in Deep Neural Networks
Jarrod Haas, William Yolland, Bernhard Rabus
Deep Neural Network Distribution Detection Neural Collapse Normalization Dictionary ResNet Based Deep Uncertainty

August 11, 2022

Uncertainty Quantification for Traffic Forecasting: A Unified Approach
Weizhu Qian, Dalin Zhang, Yan Zhao, Kai Zheng, James J. Q. Yu
Uncertainty Quantification Unified Framework Traffic Forecasting Traffic Data Spatiotemporal Correlation Deep Uncertainty

December 23, 2021

Multi-Camera Sensor Fusion for Visual Odometry using Deep Uncertainty Estimation
Nimet Kaygusuz, Oscar Mendez, Richard Bowden
Autonomous Driving Autonomous Vehicle Visual Odometry Multimodal Fusion Camera Fusion Deep Uncertainty

December 9, 2021

The Peril of Popular Deep Learning Uncertainty Estimation Methods
Yehao Liu, Matteo Pagliardini, Tatjana Chavdarova, Sebastian U. Stich
Uncertainty Estimation Bayesian Neural Network Confidence Interval Deep Uncertainty

Deep Uncertainty

Papers

Improving Uncertainty-Error Correspondence in Deep Bayesian Medical Image Segmentation

Uncertainty-Informed Volume Visualization using Implicit Neural Representation

Uncertainty-Aware Deep Neural Representations for Visual Analysis of Vector Field Data

Uncertainty Quantification with Deep Ensembles for 6D Object Pose Estimation

Uncertainty quantification and out-of-distribution detection using surjective normalizing flows

Dynamic ensemble selection based on Deep Neural Network Uncertainty Estimation for Adversarial Robustness

Evaluating the Fairness of Deep Learning Uncertainty Estimates in Medical Image Analysis

Uncertainty estimations methods for a deep learning model to aid in clinical decision-making -- a clinician's perspective

Linking Neural Collapse and L2 Normalization with Improved Out-of-Distribution Detection in Deep Neural Networks

Uncertainty Quantification for Traffic Forecasting: A Unified Approach

Multi-Camera Sensor Fusion for Visual Odometry using Deep Uncertainty Estimation

The Peril of Popular Deep Learning Uncertainty Estimation Methods