用Mamba架构提升遥感图像语义变化检测精度与效率
Mamba-FCS: Joint Spatio- Frequency Feature Fusion, Change-Guided Attention, and SeK Loss for Enhanced Semantic Change Detection in Remote Sensing
- 融合空间与频率域特征，增强边缘清晰度
- 引入变化引导注意力机制，提升小类变化检测能力
- 采用分离卡帕损失，优化类别不平衡场景下的性能
从遥感影像中进行语义变化检测（SCD）需要模型在广泛的空间上下文、计算效率和对类别不平衡地表覆盖变化的敏感性之间取得平衡。虽然卷积神经网络擅长局部特征提取但缺乏全局上下文，而变压器虽能建模全局信息但计算成本高。基于状态空间模型的最新Mamba架构通过线性复杂度和高效的长距离建模提供了有前景的解决方案。本文提出Mamba-FCS框架，基于视觉状态空间模型主干网络，包含联合时空频融合模块，整合对数幅度频域特征以增强边缘清晰度并抑制光照伪影；变化引导注意力（CGA）模块，显式关联自然交织的二值变化检测（BCD）与语义变化检测任务；以及针对类别不平衡优化的分离卡帕（SeK）损失。在SECOND和Landsat-SCD数据集上的大量实验表明，Mamba-FCS达到最先进的性能：SECOND上总体准确率88.62%，F_scd为65.78%，SeK为25.50%；Landsat-SCD上总体准确率96.25%，F_scd为89.27%，SeK为60.26%。消融分析证实各组件的独立贡献，定性评估也显示显著改进。结果表明，结合所提技术的Mamba架构在遥感语义变化检测中具有巨大潜力，树立了高效可扩展的新基准。完整代码、配置文件及预训练模型将在发表后公开。
原文摘要 · Abstract (English)
Semantic Change Detection (SCD) from remote sensing imagery requires models balancing extensive spatial context, computational efficiency, and sensitivity to class-imbalanced land-cover transitions. While Convolutional Neural Networks excel at local feature extraction but lack global context, Transformers provide global modeling at high computational costs. Recent Mamba architectures based on state-space models offer compelling solutions through linear complexity and efficient long-range modeling. In this study, we introduce Mamba-FCS, a SCD framework built upon Visual State Space Model backbone incorporating, a Joint Spatio-Frequency Fusion block incorporating log-amplitude frequency domain features to enhance edge clarity and suppress illumination artifacts, a Change-Guided Attention (CGA) module that explicitly links the naturally intertwined BCD and SCD tasks, and a Separated Kappa (SeK) loss tailored for class-imbalanced performance optimization. Extensive evaluation on SECOND and Landsat-SCD datasets shows that Mamba-FCS achieves state-of-the-art metrics, 88.62% Overall Accuracy, 65.78% F_scd, and 25.50% SeK on SECOND, 96.25% Overall Accuracy, 89.27% F_scd, and 60.26% SeK on Landsat-SCD. Ablation analyses confirm distinct contributions of each novel component, with qualitative assessments highlighting significant improvements in SCD. Our results underline the substantial potential of Mamba architectures, enhanced by proposed techniques, setting a new benchmark for effective and scalable semantic change detection in remote sensing applications. The complete source code, configuration files, and pre-trained models will be publicly available upon publication.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。