S²GFormer: A Transformer and Graph Convolution Combining Framework for Hyperspectral Image Classification

Transformer-based methods have a great ability to model nonlocal interactions between spectral and spatial information, while the local features are easily ignored. Graph convolutional neural networks (GCNs) tend to do well in exploiting neighborhood vertex interactions based on their unique aggrega...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on geoscience and remote sensing 2024, Vol.62, p.1-14
Hauptverfasser:	Huang, Shiqi, Ding, Yao, Zhang, Zhili, Yang, Aitao, Yang, Shujun, Cai, Yaoming, Cai, Weiwei
Format:	Artikel
Sprache:	eng
Schlagworte:	Computational modeling Convolution Data mining Feature extraction Follow patch mechanism Graphormer Encoder hyperspectral image (HSI) classification Hyperspectral imaging Image classification patchwise spectral embedding Training Transformers Transforms Vectors
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!