Semantic segmentation for very-high resolution (VHR) remote sensing images has been a research hotspot in the field of remote sensing image analysis. However, most existing methods still suffer from a challenge that object boundaries cannot be finely recovered. To tackle the problem, we develop a dual-stream network based on the U-Net architecture, which consists of a semantic segmentation sub-network (SSN) and an edge detection sub-network (EDN). Instead of the traditional skip connections, a

more »

... oundary attention module (BAM) is proposed to introduce the boundary information from the EDN module to the SSN module. Experiments on ISPRS Potsdam and Vaihingen datasets show that the effectiveness of the proposed network, especially in man-made objects with distinct boundaries.