Continual Unsupervised Domain Adaptation in Data-Constrained Environments

Domain adaptation (DA) techniques aim to overcome the domain shift between the source domain used for training and the target domain where testing takes place. However, current DA methods assume that the entire target domain is available during adaptation, which may not hold in practice. We introduc...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on artificial intelligence 2024-01, Vol.5 (1), p.167-178
Hauptverfasser:	Taufique, Abu Md Niamul, Jahan, Chowdhury Sadman, Savakis, Andreas
Format:	Artikel
Sprache:	eng
Schlagworte:	Adaptation models Adaptive learning Artificial intelligence continual learning (CL) Data models data-constrained learning Deep learning Training unsupervised domain adaptation (UDA) Unsupervised learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!