mlsanityData to 7 Oct 2026

One step closer to unbiased aleatoric uncertainty estimation

arXiv 2312.10469 ↗First posted 16 Dec 2023cs.LG stat.MLcited by 10

Not on the map. Why?

Abstract (arXiv)

Neural networks are powerful tools in various applications, and quantifying their uncertainty is crucial for reliable decision-making. In the deep learning field, the uncertainties are usually categorized into aleatoric (data) and epistemic (model) uncertainty. In this paper, we point out that the existing popular variance attenuation method highly overestimates aleatoric uncertainty. To address this issue, we propose a new estimation method by actively de-noising the observed data. By conducting a broad range of experiments, we demonstrate that our proposed approach provides a much closer approximation to the actual data uncertainty than the standard method.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 11 of its 21 references that are in the map. First posted on arXiv 16 Dec 2023.

Builds on

11 of 21 references.

References · 11

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  3. 2018Neural Ordinary Differential Equationscited by 3,733
  4. 2019Deep Evidential Regressioncited by 354
  5. 2015Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networkscited by 295
  6. 2023Unleashing Text-to-Image Diffusion Models for Visual Perceptioncited by 266
  7. 2022A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglementcited by 87
  8. 2021Active Learning for Deep Object Detection via Probabilistic Modelingcited by 79
  9. 2019Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCTcited by 41
  10. 2022A Quantitative Geometric Approach to Neural-Network Smoothnesscited by 16
  11. 2020On the Number of Linear Functions Composing Deep Neural Network: Towards a Refined Definition of Neural Networks Complexitycited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 3; 2026: 3.

10 papers.

  1. 2025Uncertainty Quantification for Machine Learning in Healthcare: A Surveycited by 11
  2. 2025Position: Epistemic uncertainty estimation methods are fundamentally incompletecited by 8
  3. 2024Exploring Aleatoric Uncertainty in Object Detection via Vision Foundation Modelscited by 3
  4. 2024Adaptive Sampling to Reduce Epistemic Uncertainty Using Prediction Interval-Generation Neural Networkscited by 3
  5. 2026Concerning Uncertainty -- A Systematic Survey of Uncertainty-Aware XAIcited by 2
  6. 2024Negative impact of heavy-tailed uncertainty and error distributions on the reliability of calibration statistics for machine learning regression taskscited by 1
  7. 2025Probabilistic Neural Networks (PNNs) with t-Distributed Outputs: Adaptive Prediction Intervals Beyond Gaussian Assumptionscited by 1
  8. 2026Delving Aleatoric Uncertainty in Medical Image Segmentation via Vision Foundation Modelscited by 1
  9. 2024Validation of ML-UQ calibration statistics using simulated reference values: a sensitivity analysiscited by 0
  10. 2026CUPID: A Plug-in Framework for Joint Aleatoric and Epistemic Uncertainty Estimation with a Single Modelcited by 0