GCSANet: A Global Context Spatial Attention Deep Learning Network for Remote Sensing Scene Classification

• Published in: IEEE journal of selected topics in applied earth observations and remote sensing Vol. 15; pp. 1150 - 1162
• Main Authors: Chen, Weitao, Ouyang, Shubing, Tong, Wei, Li, Xianju, Zheng, Xiongwei, Wang, Lizhe
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Attention mechanism; Classification; Computer networks; Context; Convolutional neural networks; Data mining; Datasets; Deep learning; feature channel; Feature extraction; global context information; Image analysis; Image classification; Image enhancement; Machine learning; Mountains; Neural networks; Object recognition; Performance evaluation; Remote sensing; Scene classification; Smoothness; Spatial data; Spatial discrimination learning

Deep convolutional neural networks have become an indispensable method in remote sensing image scene classification because of their powerful feature extraction capabilities. However, the ability of the models to extract multiscale features and global features on surface objects of complex scenes is...