融合ConvLSTM和多注意力机制网络的高光谱图像分类

唐婷, 潘新^*, 罗小玲, 郜晓晶

Fusion of ConvLSTM and Multi-Attention Mechanism Network for Hyperspectral Image Classification

TANG Ting, PAN Xin^*, LUO Xiao-ling, GAO Xiao-jing

使用0.5%训练样本的SV数据集的各个方法分类图 (a): 伪彩图; (b): 对应标签; (c): SVM (87.15%); (d): CDCNN (76.25%); (e): FDSSC (95.90%); (f): SSRN (92.68%); (g): DBDA (94.72%); (h): 本方法 (96.02%)