How Useful are Gradients for OOD Detection Really?

One critical challenge in deploying highly performant machine learning models in real-life applications is out of distribution (OOD) detection. Given a predictive model which is accurate on in distribution (ID) data, an OOD detection system will further equip the model with the option to defer predi...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2022-05
Hauptverfasser:	Igoe, Conor, Chung, Youngseog, Char, Ian, Schneider, Jeff
Format:	Artikel
Sprache:	eng
Schlagworte:	Machine learning Prediction models
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!