Towards Knowledge Uncertainty Estimation for Open Set Recognition

Towards Knowledge Uncertainty Estimation for Open Set Recognition

Uncertainty is ubiquitous and happens in every single prediction of Machine Learning models. The ability to estimate and quantify the uncertainty of individual predictions is arguably relevant, all the more in safety-critical applications. Real-world recognition poses multiple challenges since a mod...

Full description

Bibliographic Details
Main Authors: Catarina Pires, Marília Barandas, Letícia Fernandes, Duarte Folgado, Hugo Gamboa
Format: Article
Language:English
Published: MDPI AG 2020-10-01
Series:Machine Learning and Knowledge Extraction
Subjects:
uncertainty
machine learning
open set recognition
entropy
out-of-distribution
Online Access:https://www.mdpi.com/2504-4990/2/4/28

Internet

https://www.mdpi.com/2504-4990/2/4/28

Similar Items