A Novel Transformer Network with a CNN-Enhanced Cross-Attention Mechanism for Hyperspectral Image Classification

• Published in: Remote sensing (Basel, Switzerland) Vol. 16; no. 7; p. 1180
• Main Authors: Wang, Xinyu, Sun, Le, Lu, Chuhan, Li, Baozhu
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.04.2024
• Subjects: Algorithms; Artificial neural networks; Artificial satellites in remote sensing; Classification; Computational linguistics; convolutional neural network (CNN); data collection; Deep learning; Feature maps; hyperspectral image classification; hyperspectral imagery; Hyperspectral imaging; image analysis; Image classification; Image enhancement; Image processing; Information processing; Language processing; Machine learning; Methods; Morphology; multi-scale feature; Natural language interfaces; Neural networks; sample size; Semantics; transformer; China

Recently, with the remarkable advancements of deep learning in the field of image processing, convolutional neural networks (CNNs) have garnered widespread attention from researchers in the domain of hyperspectral image (HSI) classification. Moreover, due to the high performance demonstrated by the...