Learning to Forget for Meta-Learning via Task-and-Layer-Wise Attenuation

Few-shot learning is an emerging yet challenging problem in which the goal is to achieve generalization from only few examples. Meta-learning tackles few-shot learning via the learning of prior knowledge shared across tasks and using it to learn new tasks. One of the most representative meta-learnin...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 11 vom: 04. Nov., Seite 7718-7730
1. Verfasser:	Baik, Sungyong (VerfasserIn)
Weitere Verfasser:	Oh, Junghoon, Hong, Seokil, Lee, Kyoung Mu
Format:	Online-Aufsatz
Sprache:	English
Veröffentlicht:	2022
Zugriff auf das übergeordnete Werk:	IEEE transactions on pattern analysis and machine intelligence
Schlagworte:	Journal Article Research Support, Non-U.S. Gov't