Rethinking Uncertainty Quantification and Entanglement in Image Segmentation

• URL: http://arxiv.org/abs/2603.18792v1
• Date: Thu, 19 Mar 2026 11:43:26 GMT
• Title: Rethinking Uncertainty Quantification and Entanglement in Image Segmentation
• Abstract summary: Uncertainty (UQ) is crucial in safety-critical applications such as medical image segmentation.<n>Many methods exist for modeling AU (such as Probabilistic UNet, Diffusion) and EU (such as ensembles, MC Dropout) but it is unclear how they interact when combined.<n>We present a comprehensive empirical study covering a broad range of AU-EU model combinations, propose a metric to quantify uncertainty entanglement, and evaluate both across downstream UQ tasks.
• Score: 8.952491535016444
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Uncertainty quantification (UQ) is crucial in safety-critical applications such as medical image segmentation. Total uncertainty is typically decomposed into data-related aleatoric uncertainty (AU) and model-related epistemic uncertainty (EU). Many methods exist for modeling AU (such as Probabilistic UNet, Diffusion) and EU (such as ensembles, MC Dropout), but it is unclear how they interact when combined. Additionally, recent work has revealed substantial entanglement between AU and EU, undermining the interpretability and practical usefulness of the decomposition. We present a comprehensive empirical study covering a broad range of AU-EU model combinations, propose a metric to quantify uncertainty entanglement, and evaluate both across downstream UQ tasks. For out-of-distribution detection, ensembles exhibit consistently lower entanglement and superior performance. For ambiguity modeling and calibration the best models are dataset-dependent, with softmax/SSN-based methods performing well and Probabilistic UNets being less entangled. A softmax ensemble fares remarkably well on all tasks. Finally, we analyze potential sources of uncertainty entanglement and outline directions for mitigating this effect.

Related papers

• Set-Inclusive Uncertainty Modeling for Robust Brain Tumor Segmentation [17.88630413987641]
  We propose a probabilistic representation framework that models representations as Gaussian distributions.<n>We regularize the mean from each partial configuration toward its full-modality counterpart, while scaling the variance with the discrepancy between their aligned means.<n>Experiments on BraTS 2018 and 2020 demonstrate that our approach offers superior performance over baselines across diverse missing-modality scenarios.
  arXiv  Detail & Related papers  (2026-06-29T14:35:55Z)
• Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantification [41.04503562937318]
  Large language models (LLMs) often produce confident yet incorrect responses.<n>Self-consistency to estimate aleatoric uncertainty (AU) collapses when models are overconfident.<n>We show that cross-model semantic disagreement is higher on incorrect answers precisely when AU is low.
  arXiv  Detail & Related papers  (2026-04-18T19:00:27Z)
• Equivariant Evidential Deep Learning for Interatomic Potentials [55.6997213490859]
  Uncertainty quantification is critical for assessing the reliability of machine learning interatomic potentials in molecular dynamics simulations.<n>Existing UQ approaches for MLIPs are often limited by high computational cost or suboptimal performance.<n>We propose textitEquivariant Evidential Deep Learning for Interatomic Potentials ($texte2$IP), a backbone-agnostic framework that models atomic forces and their uncertainty jointly.
  arXiv  Detail & Related papers  (2026-02-11T02:00:25Z)
• The Illusion of Certainty: Uncertainty quantification for LLMs fails under ambiguity [48.899855816199484]
  We introduce MAQA* and AmbigQA*, the first ambiguous question-answering (QA) datasets equipped with ground-truth answer distributions.<n>We show that predictive-distribution and ensemble-based estimators are fundamentally limited under ambiguity.
  arXiv  Detail & Related papers  (2025-11-06T14:46:35Z)
• UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything Model [19.8785302359805]
  This paper presents a theoretically motivated uncertainty quantification model based on a Bayesian entropy formulation.<n>We use this formulation to train USAM, a lightweight post-hoc UQ method.<n>Our proposed deterministic USAM demonstrates superior predictive capabilities on the SA-V, MOSE, ADE20k, DAVIS, and COCO datasets.
  arXiv  Detail & Related papers  (2025-05-08T08:36:23Z)
• Uncertainty Estimation of Large Language Models in Medical Question Answering [60.72223137560633]
  Large Language Models (LLMs) show promise for natural language generation in healthcare, but risk hallucinating factually incorrect information. We benchmark popular uncertainty estimation (UE) methods with different model sizes on medical question-answering datasets. Our results show that current approaches generally perform poorly in this domain, highlighting the challenge of UE for medical applications.
  arXiv  Detail & Related papers  (2024-07-11T16:51:33Z)
• Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling [69.83976050879318]
  In large language models (LLMs), identifying sources of uncertainty is an important step toward improving reliability, trustworthiness, and interpretability. In this paper, we introduce an uncertainty decomposition framework for LLMs, called input clarification ensembling. Our approach generates a set of clarifications for the input, feeds them into an LLM, and ensembles the corresponding predictions.
  arXiv  Detail & Related papers  (2023-11-15T05:58:35Z)
• Measuring and Modeling Uncertainty Degree for Monocular Depth Estimation [50.920911532133154]
  The intrinsic ill-posedness and ordinal-sensitive nature of monocular depth estimation (MDE) models pose major challenges to the estimation of uncertainty degree. We propose to model the uncertainty of MDE models from the perspective of the inherent probability distributions. By simply introducing additional training regularization terms, our model, with surprisingly simple formations and without requiring extra modules or multiple inferences, can provide uncertainty estimations with state-of-the-art reliability.
  arXiv  Detail & Related papers  (2023-07-19T12:11:15Z)
• Ambiguity Meets Uncertainty: Investigating Uncertainty Estimation for Word Sense Disambiguation [5.55197751179213]
  Existing supervised methods treat WSD as a classification task and have achieved remarkable performance. This paper extensively studies uncertainty estimation (UE) on the benchmark designed for WSD. We examine the capability of capturing data and model uncertainties by the model with the selected UE score on well-designed test scenarios and discover that the model reflects data uncertainty satisfactorily but underestimates model uncertainty.
  arXiv  Detail & Related papers  (2023-05-22T15:18:15Z)
• Uncertainty in Extreme Multi-label Classification [81.14232824864787]
  eXtreme Multi-label Classification (XMC) is an essential task in the era of big data for web-scale machine learning applications. In this paper, we aim to investigate general uncertainty quantification approaches for tree-based XMC models with a probabilistic ensemble-based framework. In particular, we analyze label-level and instance-level uncertainty in XMC, and propose a general approximation framework based on beam search to efficiently estimate the uncertainty with a theoretical guarantee under long-tail XMC predictions.
  arXiv  Detail & Related papers  (2022-10-18T20:54:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.