paper-with-me

홈 › Papers

Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks

2024-02-29 · Bálint Mucsányi, Michael Kirchhof, Seong Joon Oh

Uncertainty quantification, once a singular task, has evolved into a spectrum of tasks, including abstained prediction, out-of-distribution detection, and aleatoric uncertainty quantification. The latest goal is disentanglement: the construction of multiple estimators that are each tailored to one and only one source of uncertainty. This paper presents the first benchmark of uncertainty disentanglement. We reimplement and evaluate a comprehensive range of uncertainty estimators, from Bayesian over evidential to deterministic ones, across a diverse range of uncertainty tasks on ImageNet. We find that, despite recent theoretical endeavors, no existing approach provides pairs of disentangled uncertainty estimators in practice. We further find that specialized uncertainty tasks are harder than predictive uncertainty tasks, where we observe saturating performance. Our results provide both practical advice for which uncertainty estimators to use for which specific task, and reveal opportunities for future research toward task-centric and disentangled uncertainties. All our reimplementations and Weights & Biases logs are available at https://github.com/bmucsanyi/untangle.

📄 PDF Abstract BibTeX arXiv:2402.19460

Code (2)

bmucsanyi/bud 공식 구현 pytorch
bmucsanyi/untangle 공식 구현 pytorch

Tasks

BenchmarkingDisentanglementOut-of-Distribution DetectionUncertainty Quantification

Similar Papers 제목 키워드 기반

Pretrained Visual Uncertainties

2024-02-26 · Michael Kirchhof, Mark Collier, Seong Joon Oh, Enkelejda Kasneci

Accurate uncertainty estimation is vital to trustworthy machine learning, yet uncertainties typically have to be learned for each task anew. This work introduces the first pretrained uncertainty modules for vision models…

Retrieval

Benchmarking Uncertainty and its Disentanglement in multi-label Chest X-Ray Classification

2025-08-06 · Simon Baur, Wojciech Samek, Jackie Ma arxiv

Reliable uncertainty quantification is crucial for trustworthy decision-making and the deployment of AI models in medical imaging. While prior work has explored the ability of neural networks to quantify predictive, epis…

Image ClassificationMedical Diagnosis

Do We Need Higher-Order Probabilities and, If So, What Do They Mean?

2013-03-27 · Judea Pearl

The apparent failure of individual probabilistic expressions to distinguish uncertainty about truths from uncertainty about probabilistic assessments have prompted researchers to seek formalisms where the two types of un…

Evaluating Epistemic Uncertainty: Beyond OOD Detection and Active Learning

2026-07-16 · Jakub Paplhám, Willem Waegeman, Eyke Hüllermeier, Vojtěch Franc arxiv

Current evaluation of epistemic uncertainty relies on tasks such as out-ofdistribution detection and active learning. However, the Bayes-optimal decision strategies for these tasks do not coincide with the scores commonl…

Active Learning

How disentangled are your classification uncertainties?

2024-08-22 · Ivo Pascal de Jong, Andreea Ioana Sburlea, Matias Valdenegro-Toro

Uncertainty Quantification in Machine Learning has progressed to predicting the source of uncertainty in a prediction: Uncertainty from stochasticity in the data (aleatoric), or uncertainty from limitations of the model …

ClassificationDisentanglementUncertainty Quantification