# One step closer to unbiased aleatoric uncertainty estimation

arXiv: https://arxiv.org/abs/2312.10469 · HTML: https://mlsanity.com/paper/2312.10469/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 21 references that are in the map.
- First posted on arXiv 16 Dec 2023.

## Builds on (most cited first, 11 of 11)

- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Deep Evidential Regression](https://mlsanity.com/paper/1910.02600/) (2019)
- [Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks](https://mlsanity.com/paper/1502.05336/) (2015)
- [Unleashing Text-to-Image Diffusion Models for Visual Perception](https://mlsanity.com/paper/2303.02153/) (2023)
- [A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement](https://mlsanity.com/paper/2204.09308/) (2022)
- [Active Learning for Deep Object Detection via Probabilistic Modeling](https://mlsanity.com/paper/2103.16130/) (2021)
- [Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCT](https://mlsanity.com/paper/1905.12806/) (2019)
- [A Quantitative Geometric Approach to Neural-Network Smoothness](https://mlsanity.com/paper/2203.01212/) (2022)
- [On the Number of Linear Functions Composing Deep Neural Network: Towards a Refined Definition of Neural Networks Complexity](https://mlsanity.com/paper/2010.12125/) (2020)

## Built on by (most cited first, 10 of 10)

- [Uncertainty Quantification for Machine Learning in Healthcare: A Survey](https://mlsanity.com/paper/2505.02874/) (2025)
- [Position: Epistemic uncertainty estimation methods are fundamentally incomplete](https://mlsanity.com/paper/2505.23506/) (2025)
- [Exploring Aleatoric Uncertainty in Object Detection via Vision Foundation Models](https://mlsanity.com/paper/2411.17767/) (2024)
- [Adaptive Sampling to Reduce Epistemic Uncertainty Using Prediction Interval-Generation Neural Networks](https://mlsanity.com/paper/2412.10570/) (2024)
- [Concerning Uncertainty -- A Systematic Survey of Uncertainty-Aware XAI](https://mlsanity.com/paper/2603.26838/) (2026)
- [Negative impact of heavy-tailed uncertainty and error distributions on the reliability of calibration statistics for machine learning regression tasks](https://mlsanity.com/paper/2402.10043/) (2024)
- [Probabilistic Neural Networks (PNNs) with t-Distributed Outputs: Adaptive Prediction Intervals Beyond Gaussian Assumptions](https://mlsanity.com/paper/2503.12354/) (2025)
- [Delving Aleatoric Uncertainty in Medical Image Segmentation via Vision Foundation Models](https://mlsanity.com/paper/2604.10963/) (2026)
- [Validation of ML-UQ calibration statistics using simulated reference values: a sensitivity analysis](https://mlsanity.com/paper/2403.00423/) (2024)
- [CUPID: A Plug-in Framework for Joint Aleatoric and Epistemic Uncertainty Estimation with a Single Model](https://mlsanity.com/paper/2603.10745/) (2026)

## 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.