融合混合注意力机制与多尺度特征增强的高分影像建筑物提取

曲海成, 梁旭

Building extraction from high-resolution images using a hybrid attention mechanism combined with multi-scale feature enhancement

QU Haicheng, LIANG Xu

表4 武汉大学建筑数据集定量对比实验结果

Tab.4 Quantitative comparison experiment results of WHU Building Dataset

方法 IoU/% F1/% Precision/% Recall/% Param/MB VGG16-U-net 86.91 92.42 90.41 94.52 18.26 DeepLab V3+ 89.07 94.23 94.15 94.32 30.61 STT 90.48 94.97 94.85 95.09 21.02 ST-UNet 89.65 — 95.16 — 26.47 BMNet 91.73 95.14 95.01 95.27 21.34