Prototype Completion for Few-Shot Learning

Few-shot learning (FSL) aims to recognize novel classes with few examples. Pre-training based methods effectively tackle the problem by pre-training a feature extractor and then fine-tuning it through the nearest centroid based meta-learning. However, results show that the fine-tuning step makes mar...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 10 vom: 22. Okt., Seite 12250-12268
1. Verfasser:	Zhang, Baoquan (VerfasserIn)
Weitere Verfasser:	Li, Xutao, Ye, Yunming, Feng, Shanshan
Format:	Online-Aufsatz
Sprache:	English
Veröffentlicht:	2023
Zugriff auf das übergeordnete Werk:	IEEE transactions on pattern analysis and machine intelligence
Schlagworte:	Journal Article