Multidimensional_Information_Expansion_and_Processing_Network_for_Hyperspectral_Image_Classification
文章链接：https://ieeexplore.ieee.org/abstract/document/10254585 （论文可见项目中名为GRSL_样刊的PDF文件）
Some details about this article
All experiments were performed using nine methods, including SVM , 2D-CNN, 3D-CNN, MCNN-CP, DPRN, DBDA, SSFTT, CEGCN, and CMR-CNN. (We select 0.5% of each class as the training set.)
Note: These methods have been included in a project that I created.
Project Repository address: https://github.com/Candy-CY/Hyperspectral-Image-Classification-Models
Reference：
（1） SVM：Classification of hyperspectral remote sensing images with support vector machines
（2） 2D-CNN：Hyperspectral image classification with deep learning models
（3） 3D-CNN：Spectral–spatial classification of hyperspectral imagery with 3D convolutional neural network
（4） MCNN-CP：Hyperspectral image classification using mixed convolutions and covariance pooling
（5） DPRN：Deep pyramidal residual networks for spectral–spatial hyperspectral image classification
（6） DBDA：Classification of hyperspectral image based on double-branch dual-attention mechanism network
（7） SSFTT：Spectral–spatial feature tokenization transformer for hyperspectral image classification
（8） CEGCN：CNN-enhanced graph convolutional network with pixel and superpixel level feature fusion for hyperspectral image classification
（9） CMR-CNN：CMR-CNN:Cross-mixing residual network for hyperspectral image classification