Beyond Single Pixel: Context Priors Guided Semi-Supervised Building Footprint Segmentation

Automated building footprint segmentation is crucial in remote sensing with widespread applications in various fields. Semi-supervised semantic segmentation (S4) methods are gaining traction in the remote sensing community as they significantly reduce the need for labor-intensive pixel-level annotations in training segmentation models. However, these methods typically rely on individual pixel-level supervision for unlabeled data, neglecting the contextual relationships between pixels. This limits their potential to exploit unlabeled data. To bridge this gap, this article proposes a novel Context Priors Guided Semi-Supervised Building Footprint Segmentation (CPG) method that leverages contextual relationships among numerous unlabeled pixels to build supervisory signals that extend beyond individual pixel-level guidance for learning on unlabeled data. The CPG comprises two main components: Spatial Context Priors Guided Pseudo-Label Regularization (SCPLR) and Semantic Context Priors Guided Representation Learning (SCPRL). By integrating contextual knowledge from both pixel spatial locations and semantic representation spaces, these components capture comprehensive class semantic attributes and enable the model to learn complete shapes of building footprints. Our approach achieves state-of-the-art performance on three publicly available building footprint segmentation datasets, validating its effectiveness.