Year: 2021
Type: conference-paper
Abstract: Neural networks are used for many real world applications, but often they have problems estimating their own confidence. This is particularly problematic for computer vision applications aimed at making high stakes decisions with humans and their lives. In this paper we make a meta-analysis of the literature, showing that most if not all computer vision applications do not use proper epistemic uncertainty quantification, which means that these models ignore their own limitations. We describe the consequences of using models without proper uncertainty quantification, and motivate the community to adopt versions of the models they use that have proper calibrated epistemic uncertainty, in order to enable out of distribution detection. We close the paper with a summary of challenges on estimating uncertainty for computer vision applications and recommendations.
Author: Matias Valdenegro-Toro
Institution: German Research Centre for Artificial Intelligence
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3154936951