Transfer Knowledge from Head to Tail: Uncertainty Calibration under Long-tailed Distribution

How to estimate the uncertainty of a given model is a crucial problem. Current calibration techniques treat different classes equally and thus implicitly assume that the distribution of training data is balanced, but ignore the fact that real-world data often follows a long-tailed distribution. In t...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) S. 19978 - 19987
Hauptverfasser:	Chen, Jiahao, Su, Bing
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 01.06.2023
Schlagworte:	Adaptation models continual Head low-shot meta or long-tail learning Tail Temperature distribution Training Training data Transfer Uncertainty
ISSN:	1063-6919
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!