The Aleatoric Uncertainty Estimation Using a Separate Formulation with Virtual Residuals
Autor: | Takumi Kawashima, Kiyoharu Aizawa, Daiki Ikami, Akari Asai, Qing Yu |
---|---|
Rok vydání: | 2021 |
Předmět: |
FOS: Computer and information sciences
Estimation Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) SIGNAL (programming language) Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology Decoupling (cosmology) 010501 environmental sciences Overfitting 01 natural sciences Regression Uncertainty estimation 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence Aleatoric music business Algorithm Regression problems 0105 earth and related environmental sciences |
Zdroj: | ICPR |
Popis: | 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. |
Databáze: | OpenAIRE |
Externí odkaz: |