A semi-supervised boundary segmentation network for remote sensing images

Accurately segmenting remote sensing images remains challenging due to the diverse target scales and ambiguous structural boundaries. In this work, we propose a semi-supervised boundary segmentation network (BS-GAN) to address these challenges. BS-GAN employs a semi-supervised learning approach to reduce dependency on labeled data while introducing a novel mixed attention (MA) mechanism to enhance segmentation accuracy by aggregating long-range contextual information. Additionally, we develop a Boundary Gating Module (BGM) to refine boundary segmentation through a multi-task learning strategy focused on boundary feature enhancement. Experimental results on three benchmark datasets demonstrate that BS-GAN achieves superior accuracy and generalization capabilities compared to existing segmentation networks.