Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning

Modern deep learning requires large-scale extensively labelled datasets for training. Few-shot learning aims to alleviate this issue by learning effectively from few labelled examples. In previously proposed few-shot visual classifiers, it is assumed that the feature manifold, where classifier decis...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2022-12
Hauptverfasser:	Bateni, Peyman, Barber, Jarred, Goyal, Raghav, Vaden Masrani, Jan-Willem van de Meent, Sigal, Leonid, Wood, Frank
Format:	Artikel
Sprache:	eng
Schlagworte:	Benchmarks Classifiers Coders Datasets Deep learning Feature extraction Machine learning
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!