Foreground Feature Attention Module Based on Unsupervised Saliency Detector for Few-Shot Learning

In recent years, few-shot learning is proposed to solve the problem of lacking samples in deep learning. However, previous works are mainly concentrated on optimizing neural network structures or augmenting the dataset while ignoring the local relationship of the images. Considering that humans pay...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE access 2021, Vol.9, p.51179-51188
Hauptverfasser:	Kong, Zhengmin, Fu, Zhuolin, Xiong, Feng, Zhang, Chenggang
Format:	Artikel
Sprache:	eng
Schlagworte:	classification Complexity theory Computer Science Computer Science, Information Systems Datasets Deep learning Detectors Engineering Engineering, Electrical & Electronic Feature extraction Few-shot learning foreground feature Image enhancement Machine learning Modules Neural networks Object recognition Prototypes Salience Science & Technology Sensors Task analysis Task complexity Technology Telecommunications Training unsupervised saliency detector
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!