Multiscale Context Aggregation Network for Building Change Detection Using High Resolution Remote Sensing Images

Jie Dong, Wufan Zhao, Shuai WangIEEE GRSL 2022 · DOI · OpenReview

Abstract

The existing methods of building change detection (CD) using remote sensing (RS) images are still deficient in handling scale variation and class imbalance problems, indicating a decrease in the robustness of small-object detection and pseudo-change information. Thus, a novel building CD framework called the multiscale context aggregation network (MSCANet) is proposed. The high-resolution network is integrated into the feature extracting stage to maintain high-resolution representations throughout the whole process. Then, multiscale context information is aggregated using a scale-aware feature pyramid module (FPM). Recognition performance can be improved from discriminant feature representation learning by using a channel–spatial attention module. Furthermore, a class-balanced loss is proposed to reduce the impact of class imbalance in long-tail datasets. Experimental results from using the LEVIR-CD and SZTAKI AirChange benchmark datasets prove the superiority of the MSCANet over the other baseline methods, with improved maximum F1 scores of 5.28 and 8.47, respectively.
BibTeX
@article{dong2022multiscale,
  author = {Jie Dong and Wufan Zhao and Shuai Wang},
  title = {{Multiscale Context Aggregation Network for Building Change Detection Using High Resolution Remote Sensing Images}},
  journal = {IEEE Geosci. Remote. Sens. Lett.},
  year = {2022},
  doi = {10.1109/lgrs.2021.3121094},
}

Loading related content...

Figure