CTF-SSCL: CNN-Transformer for Few-Shot Hyperspectral Image Classification Assisted by Semisupervised Contrastive Learning

Few-shot learning (FSL) has rapidly advanced in the hyperspectral image classification (HSIC), potentially reducing the need for laborious and expensive labeled data collection. Due to the limited receptive field, the convolutional neural network (CNN) struggles to capture long-range dependencies fo...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on geoscience and remote sensing 2024, Vol.62, p.1-17
Hauptverfasser:	Xi, Bobo, Zhang, Yun, Li, Jiaojiao, Li, Yunsong, Li, Zan, Chanussot, Jocelyn
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Benchmarks Classification Contrastive learning Convolution Data collection Effectiveness Feature extraction Few shot learning Few-shot learning (FSL) Hyperspectral imaging Image classification lightweight multiscale transformer (MSFormer) Neural networks Receptive field Semi-supervised learning semisupervised contrastive learning (SSCL) Spatial data Spatial discrimination learning Training Transformers Unsupervised learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!