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

January 16, 2024

ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation
Kim-Celine Kahl, Carsten T. Lüth, Maximilian Zenk, Klaus Maier-Hein, Paul F. Jaeger
Semantic Segmentation New Framework Uncertainty Estimation Model Uncertainty Policy Value Uncertainty Estimation Method Quantitative Validation

January 14, 2024

SpineCLUE: Automatic Vertebrae Identification Using Contrastive Learning and Uncertainty Estimation
Sheng Zhang, Minheng Chen, Junxian Wu, Ziyue Zhang, Tonglong Li, Cheng Xue, Youyong Kong
Contrastive Learning Uncertainty Estimation Vertebra Segmentation Anatomical Prior

January 13, 2024

Scalable and Efficient Methods for Uncertainty Estimation and Reduction in Deep Learning
Soyed Tuhin Ahmed
Deep Learning Variational Inference Uncertainty Estimation Bayesian Neural Network Potential Scalability Constructive Reduction Efficient Method Resistive Memory

January 10, 2024

CreINNs: Credal-Set Interval Neural Networks for Uncertainty Estimation in Classification Tasks
Kaizheng Wang, Keivan Shariatmadar, Shireen Kudukkil Manchingal, Fabio Cuzzolin, David Moens, Hans Hallez
Uncertainty Estimation Epistemic Uncertainty Classification Task Variational Bayesian Interval Estimation

January 8, 2024

Robust Calibration For Improved Weather Prediction Under Distributional Shift
Sankalp Gilda, Neel Bhandari, Wendy Mak, Andrea Panizza
Distribution Shift Uncertainty Estimation Predictive Uncertainty Robust Calibration

January 3, 2024

Robust Control Barrier Functions using Uncertainty Estimation with Application to Mobile Robots
Ersin Das, Joel W. Burdick
Application Proficiency Mobile Robot Uncertainty Estimation Control Barrier Function Safety Guarantee Safety Critical Control Safe Control Robust Controller Elastic Actuator

December 30, 2023

Automatic hip osteoarthritis grading with uncertainty estimation from computed tomography using digitally-reconstructed radiographs
Masachika Masuda, Mazen Soufi, Yoshito Otake, Keisuke Uemura, Sotaro Kono, Kazuma Takashima, Hidetoshi Hamada, Yi Gu, Masaki Takao, Seiji Okada, Nobuhiko Sugano, Yoshinobu Sato
Uncertainty Estimation Knee Osteoarthritis Disease Progression Knee Osteoarthritis Severity Digitally Reconstructed Radiograph

December 21, 2023

AdamMCMC: Combining Metropolis Adjusted Langevin with Momentum-based Optimization
Sebastian Bieringer, Gregor Kasieczka, Maximilian F. Steffen, Mathias Trabs
Uncertainty Estimation Epistemic Uncertainty Posterior Inference Momentum Based Metropolis Adjusted Langevin Algorithm

December 20, 2023

Clustering and Uncertainty Analysis to Improve the Machine Learning-based Predictions of SAFARI-1 Control Follower Assembly Axial Neutron Flux Profiles
Lesego Moloko, Pavel Bokov, Xu Wu, Kostadin Ivanov
Machine Learning Uncertainty Estimation Prediction Uncertainty Accurate Machine Learning

December 17, 2023

Scope Compliance Uncertainty Estimate
Al-Harith Farhad, Ioannis Sorokos, Mohammed Naveed Akram, Koorosh Aslansefat, Daniel Schneider
Machine Learning Native Robustness Uncertainty Estimation Model Agnostic

December 16, 2023

Unveiling Empirical Pathologies of Laplace Approximation for Uncertainty Estimation
Maksim Zhdanov, Stanislav Dereka, Sergey Kolesnikov
Uncertainty Estimation Bayesian Approach Understanding Out of Distribution Accurate Uncertainty Laplace Approximation

December 14, 2023

Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting
Anthony Chen, Huanrui Yang, Yulu Gan, Denis A Gudovskiy, Zhen Dong, Haofan Wang, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, Shanghang Zhang
Multi Task Learning Uncertainty Estimation Distribution Data Related Task Split Learning Model Splitting Distribution Classifier Cascade Ensemble

November 30, 2023

Uncertainty in Graph Contrastive Learning with Bayesian Neural Networks
Alexander Möllers, Alexander Immer, Elvin Isufi, Vincent Fortuin
Contrastive Learning High Uncertainty Anticipation Uncertainty Estimation Bayesian Neural Network Semi Supervised Node Classification Variational Bayesian

November 23, 2023

HypUC: Hyperfine Uncertainty Calibration with Gradient-boosted Corrections for Reliable Regression on Imbalanced Electrocardiograms
Uddeshya Upadhyay, Sairam Bade, Arjun Puranik, Shahir Asfahan, Melwin Babu, Francisco Lopez-Jimenez, Samuel J. Asirvatham, Ashim Prasad, Ajit Rajasekharan, Samir Awasthi, Rakesh Barve
Uncertainty Estimation Uncertainty Calibration Canine Electrocardiogram Gradient Correction Medical Time Series Probabilistic Regression

November 22, 2023

Uncertainty Estimation in Multi-Agent Distributed Learning
Gleb Radchenko, Victoria Andrea Fill
Uncertainty Estimation Multi Agent Learning AI Hardware

November 20, 2023

November 18, 2023

Estimating Uncertainty in Landslide Segmentation Models
Savinay Nagendra, Chaopeng Shen, Daniel Kifer
Uncertainty Estimation Pixel Wise Uncertainty Landslide Detection Robust Uncertainty

November 15, 2023

Uncertainty Estimation

Papers

ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation

SpineCLUE: Automatic Vertebrae Identification Using Contrastive Learning and Uncertainty Estimation

Scalable and Efficient Methods for Uncertainty Estimation and Reduction in Deep Learning

CreINNs: Credal-Set Interval Neural Networks for Uncertainty Estimation in Classification Tasks

Robust Calibration For Improved Weather Prediction Under Distributional Shift

Robust Control Barrier Functions using Uncertainty Estimation with Application to Mobile Robots

Automatic hip osteoarthritis grading with uncertainty estimation from computed tomography using digitally-reconstructed radiographs

AdamMCMC: Combining Metropolis Adjusted Langevin with Momentum-based Optimization

Clustering and Uncertainty Analysis to Improve the Machine Learning-based Predictions of SAFARI-1 Control Follower Assembly Axial Neutron Flux Profiles

Scope Compliance Uncertainty Estimate

Unveiling Empirical Pathologies of Laplace Approximation for Uncertainty Estimation

Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting

Uncertainty in Graph Contrastive Learning with Bayesian Neural Networks

HypUC: Hyperfine Uncertainty Calibration with Gradient-boosted Corrections for Reliable Regression on Imbalanced Electrocardiograms

Uncertainty Estimation in Multi-Agent Distributed Learning

Uncertainty Estimation in Contrast-Enhanced MR Image Translation with Multi-Axis Fusion

Leveraging Uncertainty Estimates To Improve Classifier Performance

Estimating Uncertainty in Landslide Segmentation Models

Model Agnostic Explainable Selective Regression via Uncertainty Estimation

Uncertainty Estimation on Sequential Labeling via Uncertainty Transmission