Rui Huang, Jincheng Zeng, Sen Gao, Yan Xing
The paper introduces a novel 3D selective scan module (3D-SSM) to improve remote sensing change detection by capturing global information and enhancing feature representation.
This research paper presents a new method for detecting changes in images taken from remote sensing, such as satellite images. The current methods struggle to effectively capture long-range dependencies between image channels, limiting their ability to represent features accurately. The authors propose a 3D selective scan module that captures both spatial and channel information, improving the understanding of the data. This new approach shows better performance in detecting changes when tested on various datasets, compared to existing methods.
