基于残差网络特征融合的高光谱图像分类

韩彦岭, 崔鹏霞, 杨树瑚, 刘业锟, 王静, 张云

Classification of hyperspectral image based on feature fusion of residual network

HAN Yanling, CUI Pengxia, YANG Shuhu, LIU Yekun, WANG Jing, ZHANG Yun

表4 传统残差网络

Tab.4 Traditional residual network

层数 卷积核大小 卷积核个数 步长 激活函数 conv11 — 16 1×1 ReLU conv12 — 16 — ReLU conv13 — 16 — ReLU pool1 2×2 — 2×2 — conv21 — 32 — ReLU conv22 — 32 — ReLU conv23 — 32 — ReLU pool2 2×2 — 2×2 — conv3 — 64 — ReLU