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3%训练样本的IP数据集的各个方法分类图 (a): 伪彩图; (b): 对应标签; (c): SVM (68.75%); (d): CDCNN (64.21%); (e): FDSSC (92.85%); (f): SSRN (91.59%); (g): DBDA (91.32%); (h): 本方法 (93.54%)