mlsanityData to 14 Oct 2026

CUPID: A Plug-in Framework for Joint Aleatoric and Epistemic Uncertainty Estimation with a Single Model

arXiv 2603.10745 ↗First posted 11 Mar 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Accurate estimation of uncertainty in deep learning is critical for deploying models in high-stakes domains such as medical diagnosis and autonomous decision-making, where overconfident predictions can lead to harmful outcomes. In practice, understanding the reason behind a model's uncertainty and the type of uncertainty it represents can support risk-aware decisions, enhance user trust, and guide additional data collection. However, many existing methods only address a single type of uncertainty or require modifications and retraining of the base model, making them difficult to adopt in real-world systems. We introduce CUPID (Comprehensive Uncertainty Plug-in estImation moDel), a general-purpose module that jointly estimates aleatoric and epistemic uncertainty without modifying or retraining the base model. CUPID can be flexibly inserted into any layer of a pretrained network. It models aleatoric uncertainty through a learned Bayesian identity mapping and captures epistemic uncertainty by analyzing the model's internal responses to structured perturbations. We evaluate CUPID across a range of tasks, including classification, regression, and out-of-distribution detection. The results show that it consistently delivers competitive performance while offering layer-wise insights into the origins of uncertainty. By making uncertainty estimation modular, interpretable, and model-agnostic, CUPID supports more transparent and trustworthy AI. Related code and data are available at https://github.com/a-Fomalhaut-a/CUPID.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 32 of its 55 references that are in the map. First posted on arXiv 11 Mar 2026.

Builds on

32 of 55 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  3. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  4. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  5. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
  6. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
  7. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 819
  8. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 732
  9. 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
  10. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 560
  11. 2020BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learningcited by 371
  12. 2018Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networkscited by 280
20 more
  1. 2021Trustworthy AI: From Principles to Practicescited by 207
  2. 2020Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Countscited by 164
  3. 2018Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flowcited by 135
  4. 2020Masksembles for Uncertainty Estimationcited by 88
  5. 2023A Review of Uncertainty Estimation and its Application in Medical Imagingcited by 59
  6. 2024Estimating Epistemic and Aleatoric Uncertainty with a Single Modelcited by 54
  7. 2021Is MC Dropout Bayesian?cited by 35
  8. 2019Training-Free Uncertainty Estimation for Dense Regression: Sensitivity as a Surrogatecited by 28
  9. 2022BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networkscited by 23
  10. 2020Calibration of Model Uncertainty for Dropout Variational Inferencecited by 18
  11. 2022Latent Discriminant deterministic Uncertaintycited by 17
  12. 2021Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectorscited by 16
  13. 2024Uncertainty Regularized Evidential Regressioncited by 13
  14. 2021Practical Evaluation of Out-of-Distribution Detection Methods for Image Classificationcited by 10
  15. 2023One step closer to unbiased aleatoric uncertainty estimationcited by 10
  16. 2024Epistemic Uncertainty Quantification For Pre-trained Neural Networkcited by 10
  17. 2023Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regressioncited by 7
  18. 2024Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimationcited by 7
  19. 2025Revisiting Gradient-based Uncertainty for Monocular Depth Estimationcited by 6
  20. 2024Uncertainty-Aware Artificial Intelligence for Gear Fault Diagnosis in Motor Drivescited by 1

Built on by

Not cited yet.