基于深度学习的SAR图像海洋涡旋自动检测模型
刘太龙1(), 谢涛1,2,3,4(), 李建1,3,4, 王超1,5, 张雪红1,3,4
Deep learning-based automatic detection model for ocean eddies in SAR images
LIU Tailong1(), XIE Tao1,2,3,4(), LI Jian1,3,4, WANG Chao1,5, ZHANG Xuehong1,3,4

图4. PMBlock结构图

Conv代表卷积层, PConv代表部分卷积, MLCA代表混合局部通道注意力, 圆圈代表逐元素相加

Fig. 4. PMBlock structure diagram. Conv represents convolutional layer, PConv represents partial convolution, MLCA represents mixed local channel attention, and the circle represents element-wise addition