The Aleatoric Uncertainty Estimation Using a Separate Formulation with Virtual Residuals

by   Takumi Kawashima, et al.

We propose a new optimization framework for aleatoric uncertainty estimation in regression problems. Existing methods can quantify the error in the target estimation, but they tend to underestimate it. To obtain the predictive uncertainty inherent in an observation, we propose a new separable formulation for the estimation of a signal and of its uncertainty, avoiding the effect of overfitting. By decoupling target estimation and uncertainty estimation, we also control the balance between signal estimation and uncertainty estimation. We conduct three types of experiments: regression with simulation data, age estimation, and depth estimation. We demonstrate that the proposed method outperforms a state-of-the-art technique for signal and uncertainty estimation.



page 7


Improving Regression Uncertainty Estimation Under Statistical Change

While deep neural networks are highly performant and successful in a wid...

On Monocular Depth Estimation and Uncertainty Quantification using Classification Approaches for Regression

Monocular depth is important in many tasks, such as 3D reconstruction an...

SLURP: Side Learning Uncertainty for Regression Problems

It has become critical for deep learning algorithms to quantify their ou...

Crowd Counting with Decomposed Uncertainty

Research in neural networks in the field of computer vision has achieved...

Variational Inference and Bayesian CNNs for Uncertainty Estimation in Multi-Factorial Bone Age Prediction

Additionally to the extensive use in clinical medicine, biological age (...

A New Distributional Ranking Loss With Uncertainty: Illustrated in Relative Depth Estimation

We propose a new approach for the problem of relative depth estimation f...

Elucidating Noisy Data via Uncertainty-Aware Robust Learning

Robust learning methods aim to learn a clean target distribution from no...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.