FSG-Net：面向高分辨率遥感变化检测的频率-空间协同门控网络

FSG-Net: Frequency-Spatial Synergistic Gated Network for High-Resolution Remote Sensing Change Detection

September 8, 2025

作者: Zhongxiang Xie, Shuangxi Miao, Yuhan Jiang, Zhewei Zhang, Jing Yao, Xuecao Li, Jianxi Huang, Pedram Ghamisi

cs.AI

摘要

高分辨率遥感影像的变化检测是地球观测应用的核心基石，但其效果常受两大关键挑战制约。首先，模型易将时间变化（如光照、季节）引起的辐射差异误判为真实变化，导致误报频发。其次，深层抽象特征与浅层细节丰富特征之间存在不可忽视的语义鸿沟，阻碍了二者的有效融合，致使变化边界模糊不清。为深入解决这些问题，我们提出了频率-空间协同门控网络（FSG-Net），这一新颖范式旨在系统性地分离语义变化与干扰变异。具体而言，FSG-Net首先在频域操作，通过差异感知小波交互模块（DAWIM）自适应地处理不同频率成分，有效抑制伪变化。随后，在空间域中，协同时空注意力模块（STSAM）增强真实变化区域的显著性，进一步优化特征。最后，轻量级门控融合单元（LGFU）利用高层语义有选择性地门控并整合浅层关键细节，成功弥合语义鸿沟。在CDD、GZ-CD和LEVIR-CD基准数据集上的全面实验验证了FSG-Net的优越性，分别以94.16%、89.51%和91.27%的F1分数确立了新的技术标杆。代码将在可能发表后发布于https://github.com/zxXie-Air/FSG-Net。

English

Change detection from high-resolution remote sensing images lies as a cornerstone of Earth observation applications, yet its efficacy is often compromised by two critical challenges. First, false alarms are prevalent as models misinterpret radiometric variations from temporal shifts (e.g., illumination, season) as genuine changes. Second, a non-negligible semantic gap between deep abstract features and shallow detail-rich features tends to obstruct their effective fusion, culminating in poorly delineated boundaries. To step further in addressing these issues, we propose the Frequency-Spatial Synergistic Gated Network (FSG-Net), a novel paradigm that aims to systematically disentangle semantic changes from nuisance variations. Specifically, FSG-Net first operates in the frequency domain, where a Discrepancy-Aware Wavelet Interaction Module (DAWIM) adaptively mitigates pseudo-changes by discerningly processing different frequency components. Subsequently, the refined features are enhanced in the spatial domain by a Synergistic Temporal-Spatial Attention Module (STSAM), which amplifies the saliency of genuine change regions. To finally bridge the semantic gap, a Lightweight Gated Fusion Unit (LGFU) leverages high-level semantics to selectively gate and integrate crucial details from shallow layers. Comprehensive experiments on the CDD, GZ-CD, and LEVIR-CD benchmarks validate the superiority of FSG-Net, establishing a new state-of-the-art with F1-scores of 94.16%, 89.51%, and 91.27%, respectively. The code will be made available at https://github.com/zxXie-Air/FSG-Net after a possible publication.