Remote sensing image change detection, being a pixel-level dense prediction task, requires both high speed and high accuracy. The redundancy within the models and detection errors, particularly missed detections, generally affect accuracy and merit further research. Moreover, the former also leads to a reduction in speed. To guarantee the efficiency of change detection, encompassing both speed and accuracy, a VMamba-based Multi-scale Feature Guiding Fusion Network (VMMCD) is proposed. This network is capable of promptly modeling global relationships and realizing multi-scale feature interaction. Specifically, the Mamba backbone is adopted to replace the commonly used CNN and Transformer backbones. By leveraging VMamba’s global modeling ability with linear computational complexity, the computational resources needed for extracting global features are reduced. Secondly, considering the characteristics of the VMamba model, a compact and efficient lightweight network architecture is devised. The aim is to reduce the model’s redundancy, thereby avoiding the extraction or introduction of interfering and redundant information. As a result, the speed and accuracy of the model are both enhanced. Finally, the Multi-scale Feature Guiding Fusion (MFGF) module is developed, which strengthens the global modeling ability of VMamba. Additionally, it enriches the interaction among multi-scale features to address the common issue of missed detections in changed areas. The proposed network achieves competitive results on three publicly available datasets—SYSU-CD, WHU-CD, and S2Looking—and surpasses the current state-of-the-art (SOTA) methods on the SYSU-CD dataset, with an of 83.35% and of 71.45%. Moreover, for inputs of size, it is more than three times faster than the current SOTA VMamba-based change detection model. This outstanding achievement demonstrates the effectiveness of our proposed approach.
Remote sensing image change detection, being a pixel-level dense prediction task, requires both high speed and high accuracy. The redundancy within the models and detection errors, particularly missed detection, generally affect accuracy and merit further research. Moreover, the former also leads to a reduction in speed. To guarantee the efficiency of change detection, encompassing both speed and accuracy, a VMamba-based Multi-scale Feature Guiding Fusion Network (VMMCD) is proposed. This network is capable of promptly modeling global relationships and realizing multi-scale feature interaction. Specifically, Mamba backbone is adopted to replace the commonly used CNN and Transformer backbones. By leveraging VMamba’s global modeling ability with linear computational complexity, the computational resources needed for extracting global features are reduced. Secondly, considering the characteristics of the VMamba model, a compact and efficient lightweight network architecture was devised. The aim is to reduce the model’s redundancy, thereby avoiding the extraction or introduction of interfering and redundant information. As a result, the speed and accuracy of the model are both enhanced. Finally, the Multi-scale Feature Guiding Fusion (MFGF) module is developed, which strengthen the global modeling ability of VMamba. Additionally, it enriches the interaction among multi-scale features to address the common issue of missed detection in changed areas. The proposed network has achieved competitive results on three datasets, and remarkably surpasses the current state-of-the-art performance on SYSU-CD, with F1 of 83.35% and IoU of 71.45%. Moreover, for inputs of 256×256 size, it is more than three times faster than the current state-of-the-art Mamba-based change detection model. This outstanding achievement demonstrates the effectiveness of our proposed approach.
22 April 2026 in IEEE Transactions on Geoscience and Remote Sensing
Remote sensing semantic change detection (RSSCD), which identifies pixel-level ground semantic changes by analyzing multi-temporal data, is widely used in fields such as urban planning and disaster monitoring. However, Most of the current datasets only contain two temporal phases, which provide insufficient information, leading to overlook areas with subtle changes and mistakenly detect non-change areas with significant differences. Moreover, changes with diverse scales and directional distributions make it difficult to localize them accurately. Besides, class imbalance further degrades detection performance. To address these issues, this paper proposes a novel Mamba-based multi-dimensional spatiotemporal scanning method. Firstly, temporal interpolation is applied to bi-temporal images, enabling high-dimensional spatiotemporal feature extraction through global interaction with linear complexity. Secondly, the shallow feature extraction module in the above model is improved and a set of diagonal scanning directions are added to better capture multi-scale and omnidirectional changes. Finally, a Consistency Dynamic Weighted Loss(CDW Loss) is introduced to mitigate class imbalance. The proposed method achieves significant improvements in the Separated Kappa (SeK) metric, a comprehensive indicator for semantic change detection, outperforming the current state-of-the-art method(ChangeMamba) by 17.67%, 4.54% and 20.80% on the Landsat-SCD, SECOND, and Hi-UCD datasets respectively, in the absence of the proposed CDW Loss.