SAM-Based Building Change Detection with Distribution-Aware Fourier Adaptation and Edge-Constrained Warping
Yun-Cheng Li, Sen Lei, Yi-Tao Zhao, Heng-Chao Li, Jun Li, Antonio Plaza
TL;DR
This work addresses the challenges of building change detection in remote sensing when applying SAM by introducing FAEWNet, which combines a Distribution-Aware Fourier Aggregated Adapter (DAFA) with an edge-constrained flow-based alignment. The model builds on a SAM-based encoder in a weight-sharing Siamese framework and uses TTAG for temporal fusion, a final global-attention DAFA, and a Multiscale Aware Flow Aggregation (MSAFA) for robust, edge-preserving change maps. Empirical results on LEVIR-CD, S2Looking, and WHU-CD show state-of-the-art performance with notable gains in recall, F1, and IoU, along with thorough ablations validating the contributions of DAFA and MSAFA. The approach enhances change detection in heterogeneous urban scenes and provides a practical, high-precision tool for disaster assessment, urban monitoring, and related remote sensing applications.
Abstract
Building change detection remains challenging for urban development, disaster assessment, and military reconnaissance. While foundation models like Segment Anything Model (SAM) show strong segmentation capabilities, SAM is limited in the task of building change detection due to domain gap issues. Existing adapter-based fine-tuning approaches face challenges with imbalanced building distribution, resulting in poor detection of subtle changes and inaccurate edge extraction. Additionally, bi-temporal misalignment in change detection, typically addressed by optical flow, remains vulnerable to background noises. This affects the detection of building changes and compromises both detection accuracy and edge recognition. To tackle these challenges, we propose a new SAM-Based Network with Distribution-Aware Fourier Adaptation and Edge-Constrained Warping (FAEWNet) for building change detection. FAEWNet utilizes the SAM encoder to extract rich visual features from remote sensing images. To guide SAM in focusing on specific ground objects in remote sensing scenes, we propose a Distribution-Aware Fourier Aggregated Adapter to aggregate task-oriented changed information. This adapter not only effectively addresses the domain gap issue, but also pays attention to the distribution of changed buildings. Furthermore, to mitigate noise interference and misalignment in height offset estimation, we design a novel flow module that refines building edge extraction and enhances the perception of changed buildings. Our state-of-the-art results on the LEVIR-CD, S2Looking and WHU-CD datasets highlight the effectiveness of FAEWNet. The code is available at https://github.com/SUPERMAN123000/FAEWNet.