CD-Mamba: Cloud detection with long-range spatial dependency modeling
This work addresses cloud detection for remote sensing data, which is an incremental improvement by combining existing techniques for better accuracy.
The paper tackles cloud detection in remote sensing images by addressing short-range spatial redundancies and long-range atmospheric similarities among cloud patches, proposing CD-Mamba, a hybrid model that integrates convolution and Mamba's state-space modeling, which demonstrates superior performance over existing methods in experiments.
Remote sensing images are frequently obscured by cloud cover, posing significant challenges to data integrity and reliability. Effective cloud detection requires addressing both short-range spatial redundancies and long-range atmospheric similarities among cloud patches. Convolutional neural networks are effective at capturing local spatial dependencies, while Mamba has strong capabilities in modeling long-range dependencies. To fully leverage both local spatial relations and long-range dependencies, we propose CD-Mamba, a hybrid model that integrates convolution and Mamba's state-space modeling into a unified cloud detection network. CD-Mamba is designed to comprehensively capture pixelwise textural details and long term patchwise dependencies for cloud detection. This design enables CD-Mamba to manage both pixel-wise interactions and extensive patch-wise dependencies simultaneously, improving detection accuracy across diverse spatial scales. Extensive experiments validate the effectiveness of CD-Mamba and demonstrate its superior performance over existing methods.