Task-Related Saliency for Few-Shot Image Classification

A weakness of the existing metric-based few-shot classification method is that task-unrelated objects or backgrounds may mislead the model since the small number of samples in the support set is insufficient to reveal the task-related targets. An essential cue of human wisdom in the few-shot classif...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transaction on neural networks and learning systems 2024-08, Vol.35 (8), p.10751-10763
Hauptverfasser:	Zhou, Zhenyu, Luo, Lei, Zhou, Sihang, Li, Wang, Yang, Xihong, Liu, Xinwang, Zhu, En
Format:	Artikel
Sprache:	eng
Schlagworte:	Adaptation models Analytical models Feature extraction Few-shot classification Image classification Measurement Prototypes saliency sensitive module (SSM) self-training Task analysis task-related saliency
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!