One step closer to unbiased aleatoric uncertainty estimation
This addresses the need for reliable uncertainty quantification in deep learning applications, though it appears incremental as it improves upon an existing method.
The paper tackled the problem of existing methods overestimating aleatoric uncertainty in neural networks by proposing a new estimation method that actively de-noises observed data, demonstrating it provides a much closer approximation to actual data uncertainty.
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.