Mamba-FCS: Joint Spatio- Frequency Feature Fusion, Change-Guided Attention, and SeK Loss for Enhanced Semantic Change Detection in Remote Sensing

TL;DR

This paper introduces Mamba-FCS, a novel framework for semantic change detection in remote sensing that combines spatio-frequency fusion, change-guided attention, and a specialized loss to improve accuracy and efficiency.

Contribution

It presents a new Mamba-FCS architecture with innovative modules like joint spatio-frequency fusion, change-guided attention, and SeK loss, achieving state-of-the-art results.

Findings

Achieves 88.62% accuracy on SECOND dataset.

Outperforms existing methods in F_scd and SeK metrics.

Ablation studies confirm the effectiveness of each component.

Abstract

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.