Distribution Shift Inversion for Out-of-Distribution Prediction

Machine learning society has witnessed the emergence of a myriad of Out-of-Distribution (OoD) algorithms, which address the distribution shift between the training and the testing distribution by searching for a unified predictor or invariant feature representation. However, the task of directly mit...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) S. 3592 - 3602
Hauptverfasser:	Yu, Runpeng, Liu, Songhua, Yang, Xingyi, Wang, Xinchao
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 01.06.2023
Schlagworte:	continual Gaussian noise low-shot Machine learning Machine learning algorithms meta or long-tail learning Performance gain Prediction algorithms Predictive models Training Transfer
ISSN:	1063-6919
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!