Publikation

I Find Your Lack of Uncertainty in Computer Vision Disturbing

Matias Valdenegro-Toro

In: IEEE/CVF. International Conference on Computer Vision and Pattern Recognition (CVPR-2021) befindet sich LatinX in CV Workshop @ CVPR 2021 June 19-25 Online IEEE 1/2021.

Abstrakt

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 f 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.

cvpr-meta-analysis-uncertainty-computer-vision.pdf (pdf, 2 MB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence