Metrics assess uncertainty structure and distribution for regression models.
problem Quantifying uncertainty in high-dimensional and nonlinear regression tasks.
method Two bounded comparison metrics for uncertainty structure and distribution.
result DNNs and DNOs provide encouraging uncertainty metric values in high dimensions.
Paper analyzes uncertainty metrics in ensemble learning for healthcare AI.
problem Selecting appropriate uncertainty metrics for ensemble learners in healthcare AI.
method Rigorous analysis of two uncertainty metrics: ensemble mean and variance.
result Ensemble mean is preferable to ensemble variance for decision making in healthcare AI.
Decision-alignment evaluates uncertainty quantification for decision-relevant UQ
problem Evaluation of uncertainty quantification metrics
method Introduce decision-alignment
result Proper scoring rules align with decision utility
Accurately estimating uncertainties in neural network predictions is of great importance in building trusted DNNs-based models, and there is an increasing interest in providing accurate uncertainty estimation on many tasks, such as security cameras and autonomous driving vehicles. In this paper, we focus on the two mai…
Spatially-aware metrics improve uncertainty evaluation in segmentation.
problem Uncertainty evaluation metrics treat voxels independently, ignoring spatial context.
method Proposed three spatially aware metrics incorporating structural and boundary information.
result Improved alignment with clinically important factors and better discrimination between uncertainty patterns.
Sharp bounds for distortion risk metrics under uncertain distributions.
problem Modeling risk metrics under distributional uncertainty.
method Established bounds for distortion risk metrics using specific features of underlying distributions.
result Identified worst- and best-case values of distortion risk metrics.
Novel framework for uncertainty quantification in metric spaces.
problem Uncertainty quantification in regression models with metric responses.
method Developed algorithms for large datasets, agnostic to predictive models, with asymptotic and non-asymptotic guarantees.
result Asymptotic and non-asymptotic guarantees for special cases, demonstrated in clinical applications.
New method quantifies classifier uncertainty, revealing large variability in performance metrics.
problem Uncertainty in classifier performance metrics due to small data sets.
method Probability model of the confusion matrix to quantify uncertainty.
result Large uncertainties in classification performance metrics can lead to misleading conclusions.
New metrics improve uncertainty estimation on graph data.
problem Current GNNs focus only on nodewise scores, limiting uncertainty estimation.
method Proposed edgewise metrics for uncertainty estimation on graphs.
result GNN models with structured prediction perform better in uncertainty estimation.
The paper quantifies uncertainty in aggregated machine learning metrics.
problem Uncertainty in summarizing model performance across multiple tasks.
method Statistical methodologies including bootstrapping and Bayesian modeling.
result Insights into model performance dominance for specific tasks.
This paper visualizes uncertainty in classifier performance metrics.
problem Overemphasis on model performance metrics risks overlooking uncertainty.
method Developed visualizations of confusion matrix metric distributions.
result Uncertainty in performance metrics can overshadow model differences.
New method uses interval-based metric to validate prediction uncertainty in machine learning.
problem Validation of prediction uncertainty in machine learning regression tasks is unreliable due to heavy-tailed distributions.
method Shift from variance-based metrics to interval-based Prediction Interval Coverage Probability (PICP).
result PICP method more quickly and reliably tests prediction intervals than variance-based metrics.
This work introduces a new metric for comparing imprecise probability models.
problem Quantifying differences between imprecise probability models.
method Integral imprecise probability metric framework based on Choquet integral.
result IIPM enables comparison across different imprecise probability models and quantifies epistemic uncertainty.
New method uses generative models to estimate aleatoric uncertainty without strict data restrictions.
problem Estimating aleatoric uncertainty with limited data distribution or dimensionality.
method Conditional generative models and two metrics for measuring distributional discrepancies.
result Metrics accurately measure conditional distributional discrepancies and train competitive models.
Research uses CPS to estimate uncertainty in ML radio metric models.
problem Estimating uncertainty in machine learning models for radio metrics and path loss.
method Conformal Prediction (CP) in Conformal Predictive Systems (CPS) with diverse difficulty estimators.
result CPS models maintain high coverage and reliability across different cities.
COMPASS improves uncertainty quantification for medical segmentation metrics.
problem Uncertainty quantification for medical segmentation metrics is crucial for clinical decision-making.
method COMPASS leverages deep neural network inductive biases to generate efficient, metric-based conformal prediction intervals.
result COMPASS produces significantly tighter intervals than traditional conformal prediction methods on medical image segmentation tasks.
Uncertainty Toolbox aids in assessing and improving uncertainty quantification in machine learning.
problem Disparate evaluation metrics and implementations hinder direct comparison of uncertainty quantification results.
method Provides an open-source Python library for assessing, visualizing, and improving uncertainty quantification.
result Facilitates more accurate and comparable uncertainty quantification across different works.
We study the quantification of uncertainty of Convolutional Neural Networks (CNNs) based on gradient metrics. Unlike the classical softmax entropy, such metrics gather information from all layers of the CNN. We show for the EMNIST digits data set that for several such metrics we achieve the same meta classification acc…
As deep learning applications are becoming more and more pervasive in robotics, the question of evaluating the reliability of inferences becomes a central question in the robotics community. This domain, known as predictive uncertainty, has come under the scrutiny of research groups developing Bayesian approaches adapt…
This paper compares uncertainty estimation methods for deep learning in autonomous vehicles.
problem Ensuring safety in autonomous vehicles through accurate uncertainty quantification in deep learning models.
method A comparative survey of uncertainty quantification methods in deep neural networks.
result Different methods for uncertainty quantification in DNNs have advantages and downsides for specific AV tasks and types of uncertainty.
Distance metric learning (DML) has been studied extensively in the past decades for its superior performance with distance-based algorithms. Most of the existing methods propose to learn a distance metric with pairwise or triplet constraints. However, the number of constraints is quadratic or even cubic in the number o…
New method selects equivariant models using uncertainty metrics.
problem Selecting equivariant models among pretrained ones with varying symmetry biases.
method Uncertainty-aware model selection using frequentist, Bayesian, and calibration-based measures.
result Bayesian model evidence often misaligns with predictive performance.
Paper proposes a new method to quantify uncertainty in machine learning models.
problem Quantifying uncertainty in multiclass classification models.
method Distance-based approach using Integral Probability Metrics (IPMs).
result Effective uncertainty measures for multiclass classification.
The paper introduces algorithms for uncertainty quantification in metric spaces.
problem Uncertainty quantification in regression models defined on metric spaces.
method Proposes conformal and kNN prediction algorithms for metric spaces.
result Both algorithms provide finite-sample guarantees and improve local coverage calibration.
Survey on uncertainty in ML and DL, covering sources, quantification, and decision-making.
problem Understanding and quantifying uncertainty in ML and DL for risk-sensitive applications.
method Structured review of literature, categorizing uncertainty, assessing uncertainty quantification techniques.
result Broadened scope of uncertainty discussion and updated DL uncertainty quantification methods.
Proposes a neural network loss function for better uncertainty estimation.
problem Challenges in estimating predictive uncertainty of neural networks.
method Bayesian Validation Metric (BVM) framework with ensemble learning.
result Competitive and robust uncertainty estimation on in-distribution and out-of-distribution data.
New method accounts for uncertainty in medical AI evaluations.
problem Uncertainty in ground truth affects AI model performance estimates.
method Statistical aggregation approach to infer probabilities of medical conditions.
result Performance estimates are significantly lower when uncertainty is accounted for.
A new probabilistic approach improves deep metric learning by considering image uncertainties and class-specific variances.
problem Proxy-based deep metric learning struggles with image uncertainties and class-specific structures.
method Introduces non-isotropic probabilistic proxy-based deep metric learning using directional von Mises-Fisher distributions.
result Improves generalization performance and competitive on standard benchmarks.
New research shows calibration error is flawed when dealing with model uncertainty.
problem Current model evaluation techniques conflate model uncertainty with aleatoric uncertainty.
method Posterior predictive checks to evaluate deep learning models.
result Calibration error and variants are incorrect when model uncertainty is present.
Paper decomposes risk into aleatoric and epistemic uncertainties and generates predictive uncertainty measures.
problem Unclear relationships between various predictive uncertainty measures in literature.
method Bayesian estimation to decompose risk into aleatoric and epistemic uncertainties, generating different predictive uncertainty measures.
result Experimental validation confirms usefulness of derived predictive uncertainty measures for detecting out-of-distribution and misclassified instances.
The paper calibrates uncertainty in dropout variational inference models.
problem Miscalibration of model uncertainty in dropout variational inference.
method Logit scaling methods are extended to recalibrate model uncertainty.
result Logit scaling reduces miscalibration, improving reliability of predictions.
UDJ-FL framework achieves multiple distributive justice-based fairness metrics in federated learning.
problem Ensuring fairness in federated learning across different client data distributions.
method UDJ-FL framework uses aleatoric uncertainty-based client weighing and fair resource allocation techniques.
result UDJ-FL achieves egalitarian, utilitarian, Rawls' difference principle, and desert-based fairness metrics.
Optimal transport for measures on noisy tree metrics is solved with robust approach.
problem Optimal transport problem for measures on noisy tree metrics.
method Max-min robust optimal transport approach considering uncertainty sets of tree metrics.
result Robust optimal transport admits a closed-form expression for fast computation.
Model uncertainty obtained by variational Bayesian inference with Monte Carlo dropout is prone to miscalibration. The uncertainty does not represent the model error well. In this paper, temperature scaling is extended to dropout variational inference to calibrate model uncertainty. Expected uncertainty calibration erro…
Bayesian Neural Networks improve uncertainty modeling in facial emotion recognition.
problem High aleatoric uncertainty and visual ambiguity in facial emotion recognition.
method Bayesian Neural Networks approximated using MC-Dropout, MC-DropConnect, or Ensemble methods.
result Bayesian Neural Networks produce more human-like output probabilities.
Improves reliability of medical diagnosis uncertainty estimates.
problem Label uncertainty in medical diagnosis.
method Post-hoc alpha-calibration method for neural network classifiers. result Significantly enhances reliability of uncertainty estimates.
We propose orthogonality as a necessary condition for disentangling aleatoric and epistemic uncertainty.
problem Jointly estimating aleatoric and epistemic uncertainty is problematic and non-trivial.
method We propose orthogonality as a necessary condition for disentanglement and construct UDE to measure orthogonality and consistency.
result Orthogonality and consistency are necessary and sufficient criteria for disentanglement.
Bayesian autoencoders quantify anomaly uncertainty for safer machine learning.
problem Lack of uncertainty quantification in autoencoders for anomaly detection.
method Formulated Bayesian autoencoders to quantify epistemic and aleatoric anomalies.
result Demonstrated effectiveness of BAEs on benchmark and real datasets.
Estimating how uncertain an AI system is in its predictions is important to improve the safety of such systems. Uncertainty in predictive can result from uncertainty in model parameters, irreducible data uncertainty and uncertainty due to distributional mismatch between the test and training data distributions. Differe…
We present a simple case study, demonstrating that Variational Information Bottleneck (VIB) can improve a network's classification calibration as well as its ability to detect out-of-distribution data. Without explicitly being designed to do so, VIB gives two natural metrics for handling and quantifying uncertainty.
Study pitfalls of deep learning ensembles in uncertainty estimation.
problem Pitfalls in in-domain uncertainty estimation and ensembling in deep learning.
method Exploration of standards for uncertainty quantification and broad study of ensembling techniques.
result Many sophisticated ensembling techniques are equivalent to a simple ensemble of few networks.
CCE improves anomaly detection metrics by measuring both confidence and consistency.
problem Existing anomaly detection metrics lack discriminative power, hyperparameter dependency, and robustness to perturbations.
method CCE uses Bayesian estimation to quantify uncertainty and constructs global and event-level confidence and consistency scores.
result CCE demonstrates strict boundedness, robustness, and linear time complexity.
Study evaluates machine learning methods for uncertainty quantification in complex systems.
problem Accurately quantify epistemic and aleatoric uncertainties in complex dynamical systems.
method Examined Gaussian processes, UQ-augmented neural networks (ENN, BNN, D-NN, G-NN) on two model data sets.
result Concluded on model architecture and hyperparameter tuning for improved UQ accuracy.
The paper introduces a new metric to quantify uncertainty's impact on multiple objectives.
problem Quantifying the impact of uncertainty on multiple objectives in complex systems.
method Proposes the mean multi-objective cost of uncertainty (multi-objective MOCU) to quantify uncertainty.
result Demonstrates the effectiveness of the multi-objective MOCU in real-world applications.
CRAUM-Net improves salient object detection with context and uncertainty modeling.
problem Accurate salient object detection with precise boundary delineation.
method Contextual Recursive Attention with Uncertainty Modeling, multi-scale context aggregation, attention mechanisms, edge-aware decoder, Monte Carlo Dropout.
result Superior performance in producing accurate and reliable saliency maps.
Proposes a simple method to explain aleatoric uncertainty in neural networks.
problem Lack of transparent explanations for uncertainty estimates in AI models.
method Adapting a neural network with Gaussian output to estimate predictive variance and applying explainers to the variance output.
result The proposed method explains uncertainty more reliably than complex approaches and outperforms them in most settings.
Bayesian Neural Networks show unexpected collapse of epistemic uncertainty with large models and little data.
problem Unexpected collapse of epistemic uncertainty in Bayesian Neural Networks.
method Experiments with varying model size and training data size.
result Epistemic uncertainty collapses in the presence of large models and sometimes little data.
Efficient neural network ensembles improve image classification reliability and uncertainty quantification.
problem Uncertainty in neural network predictions for industrial image classification.
method Investigated efficient neural network ensembles (snapshot, batch, multi-input multi-output) for image classification reliability and uncertainty quantification.
result Batch ensemble is a cost-effective and competitive alternative to deep ensembles, offering savings in training and test time.