Uncertainty Estimation

Uncertainty estimation in machine learning aims to quantify the reliability of model predictions, addressing the critical need for trustworthy AI systems. Current research focuses on improving uncertainty quantification across diverse model architectures, including Bayesian neural networks, ensembles, and novel methods like evidential deep learning and conformal prediction, often tailored to specific application domains (e.g., medical imaging, natural language processing). Accurate uncertainty estimation is crucial for responsible AI deployment, enabling better decision-making in high-stakes applications and fostering greater trust in AI-driven outcomes across various scientific and practical fields. This includes identifying unreliable predictions, improving model calibration, and mitigating issues like hallucinations in large language models.

Papers

April 29, 2022

Tailored Uncertainty Estimation for Deep Learning Systems
Joachim Sicking, Maram Akila, Jan David Schneider, Fabian Hüger, Peter Schlicht, Tim Wirtz, Stefan Wrobel
Uncertainty Quantification High Uncertainty Anticipation Uncertainty Estimation Deep Learning System Uncertainty Estimation Method Estimation Performance

April 25, 2022

Data Uncertainty without Prediction Models
Bongjoon Park, Eunkyung Koh
Machine Learning Uncertainty Estimation Prediction Model Uncertainty Estimation Method Data Uncertainty

April 21, 2022

Scalable Sensitivity and Uncertainty Analysis for Causal-Effect Estimates of Continuous-Valued Interventions
Andrew Jesson, Alyson Douglas, Peter Manshausen, Maëlys Solal, Nicolai Meinshausen, Philip Stier, Yarin Gal, Uri Shalit
Uncertainty Estimation Causal Effect Health Intervention Sensitivity Aware Dose Response Valued Treatment Marginal Sensitivity Model

April 1, 2022

Autoencoder Attractors for Uncertainty Estimation
Steve Dias Da Cruz, Bertram Taetz, Thomas Stifter, Didier Stricker
Machine Learning Model Uncertainty Estimation Synthetic Dataset Autoencoder Model Attractor Network

March 16, 2022

Layer Ensembles: A Single-Pass Uncertainty Estimation in Deep Learning for Segmentation
Kaisar Kushibar, Víctor Manuel Campello, Lidia Garrucho Moras, Akis Linardos, Petia Radeva, Karim Lekadir
Deep Learning Uncertainty Quantification Segmentation Based Approach Uncertainty Estimation Deep Ensemble Pixel Wise Uncertainty Uncertainty Estimation Method Layer Ensemble

March 14, 2022

Uncertainty Estimation for Language Reward Models
Adam Gleave, Geoffrey Irving
Language Model Active Learning Uncertainty Estimation Reward Model Language Reward

March 8, 2022

Self-Supervised Domain Calibration and Uncertainty Estimation for Place Recognition
Pierre-Yves Lajoie, Giovanni Beltrame
Uncertainty Estimation Place Recognition Pose Graph Optimization Domain Calibration

March 4, 2022

Uncertainty Estimation for Heatmap-based Landmark Localization
Lawrence Schobs, Andrew J. Swift, Haiping Lu
Uncertainty Estimation Anatomical Landmark Detection Soft Landmark Binning Method Landmark Localization Cephalometric Analysis

March 3, 2022

STUN: Self-Teaching Uncertainty Estimation for Place Recognition
Kaiwen Cai, Chris Xiaoxuan Lu, Xiaowei Huang
Uncertainty Estimation Place Recognition Prediction Uncertainty Location Prediction

February 28, 2022

February 25, 2022

Deep Dirichlet uncertainty for unsupervised out-of-distribution detection of eye fundus photographs in glaucoma screening
Teresa Araújo, Guilherme Aresta, Hrvoje Bogunovic
Uncertainty Estimation Fundus Image Glaucoma Diagnosis Color Fundus Retinal Fundus Glaucoma Challenge Dirichlet Process Class Probability Unsupervised Out of Distribution Detection

February 24, 2022

On Monocular Depth Estimation and Uncertainty Quantification using Classification Approaches for Regression
Xuanlong Yu, Gianni Franchi, Emanuel Aldea
Uncertainty Quantification Uncertainty Estimation Monocular Depth Estimation Novel Regression Monocular Depth Classification Algorithm Regression via Classification

February 22, 2022

On Uncertainty Estimation by Tree-based Surrogate Models in Sequential Model-based Optimization
Jungtaek Kim, Seungjin Choi
Decision Tree Uncertainty Estimation Surrogate Model Bootstrapping End to End Model Based Optimization Sequential Optimization Black Box Optimization Problem Random Tree

February 19, 2022

February 3, 2022

Maximum Likelihood Uncertainty Estimation: Robustness to Outliers
Deebul S. Nair, Nico Hochgeschwender, Miguel A. Olivares-Mendez
Native Robustness Uncertainty Estimation Distribution Data Global Outlier Uncertainty Estimation Method Better Uncertainty Estimation

January 10, 2022

A Study on Mitigating Hard Boundaries of Decision-Tree-based Uncertainty Estimates for AI Models
Pascal Gerber, Lisa Jöckel, Michael Kläs
Study Feature Decision Tree Uncertainty Estimation Artificial Intelligence Model Uncertain Boundary Uncertainty Cluster Uncertainty Wrapper

January 5, 2022

Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation
Vincent Mai, Kaustubh Mani, Liam Paull
Uncertainty Estimation Model Free Deep Reinforcement Learning Sample Efficient Reinforcement Learning Noisy Supervision

December 27, 2021

Transformer Uncertainty Estimation with Hierarchical Stochastic Attention
Jiahuan Pei, Cheng Wang, György Szarvas
Transformer Model Uncertainty Estimation Transformer Based Structure Transformer Prediction

Uncertainty Estimation

Papers

Tailored Uncertainty Estimation for Deep Learning Systems

Data Uncertainty without Prediction Models

Scalable Sensitivity and Uncertainty Analysis for Causal-Effect Estimates of Continuous-Valued Interventions

Autoencoder Attractors for Uncertainty Estimation

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

Uncertainty Estimation for Language Reward Models

Self-Supervised Domain Calibration and Uncertainty Estimation for Place Recognition

Uncertainty Estimation for Heatmap-based Landmark Localization

STUN: Self-Teaching Uncertainty Estimation for Place Recognition

TEScalib: Targetless Extrinsic Self-Calibration of LiDAR and Stereo Camera for Automated Driving Vehicles with Uncertainty Analysis

Uncertainty Estimation for Computed Tomography with a Linearised Deep Image Prior

Deep Dirichlet uncertainty for unsupervised out-of-distribution detection of eye fundus photographs in glaucoma screening

On Monocular Depth Estimation and Uncertainty Quantification using Classification Approaches for Regression

On Uncertainty Estimation by Tree-based Surrogate Models in Sequential Model-based Optimization

Accurate Prediction and Uncertainty Estimation using Decoupled Prediction Interval Networks

Graph Reparameterizations for Enabling 1000+ Monte Carlo Iterations in Bayesian Deep Neural Networks

Maximum Likelihood Uncertainty Estimation: Robustness to Outliers

A Study on Mitigating Hard Boundaries of Decision-Tree-based Uncertainty Estimates for AI Models

Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation

Transformer Uncertainty Estimation with Hierarchical Stochastic Attention