LECloud: Efficient Cloud and Cloud-Shadow Segmentation Based on Windowed State Space Model and Lightweight Attention Mechanism.
Saved in:
| Title: | LECloud: Efficient Cloud and Cloud-Shadow Segmentation Based on Windowed State Space Model and Lightweight Attention Mechanism. |
|---|---|
| Authors: | Lu, Ao1 (AUTHOR), Wang, Junzhe1,2 (AUTHOR), Guo, Tengyue1,2,3 (AUTHOR), Wang, Zhiwei3,4 (AUTHOR), Xia, Min1,4 (AUTHOR) xiamin@nuist.edu.cn |
| Source: | Remote Sensing. May2026, Vol. 18 Issue 9, p1341. 26p. |
| Subjects: | Image segmentation, State-space methods, Remote sensing, Image processing, Computer performance, Deep learning |
| Abstract: | Highlights: What are the main findings? An efficient cloud segmentation network, LECloud, is proposed, integrating windowed state space models (LocalMamba) and lightweight channel attention mechanisms (ECA-Net); The network achieves efficiency optimizations with a 7.7% parameter reduction and a 9.4% inference speed increase while maintaining nearly unchanged accuracy, verifying the effectiveness of windowed models and lightweight attention. What are the implications of the main findings? It offers a favorable accuracy–efficiency trade-off for cloud segmentation under tight GPU memory and compute budgets, as quantified on a specified workstation-class GPU in the Results; embedded edge or on-board deployment is not experimentally validated here and is noted as future work, consistent with the Introduction; The model demonstrates strong generalization and robustness across multiple remote sensing datasets, providing critical empirical references for future research on efficient remote sensing segmentation architectures. Accurate cloud and cloud-shadow segmentation is a crucial step in optical remote sensing image preprocessing, playing a significant role in subsequent applications such as land-cover classification and change detection. However, the complexity of cloud/shadow shapes and noise interference (e.g., snow and ice, buildings, complex backgrounds, and atmospheric optics) make this task challenging. Although existing deep learning methods have achieved remarkable results in cloud segmentation tasks, a better balance between computational efficiency and segmentation accuracy is still needed. Traditional deep learning models have good detail and generalization capabilities due to their local feature extraction ability and spatial invariance, but they are relatively weak in processing global context information, leading to false positives and false negatives in complex scenarios. Encoders based on state space models (such as VMamba) can effectively capture global context through long-range dependency modeling, but there is still room for optimization in computational efficiency. Additionally, complex attention mechanisms (such as CBAM) can improve feature representation capability, but the large number of parameters limits the deployment efficiency of models. This paper conducts a systematic architectural exploration of the MCloudX cloud segmentation network, seeking a balance between efficiency and accuracy from three directions: backbone network modernization, encoder efficiency optimization, and attention mechanism lightweighting. Through comprehensive ablation experiments on SPARCS and L8-Biome datasets, we systematically evaluate the independent and synergistic effects of each component and validate them on Biome_3 and SPARCS datasets. Experimental results show that the proposed optimization configuration (ResNet50+LocalMamba+ECA-Net) significantly improves computational efficiency while maintaining comparable accuracy to the baseline. We name this optimization configuration LECloud, providing valuable empirical references for future research on efficient remote sensing segmentation architectures. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Highlights: What are the main findings? An efficient cloud segmentation network, LECloud, is proposed, integrating windowed state space models (LocalMamba) and lightweight channel attention mechanisms (ECA-Net); The network achieves efficiency optimizations with a 7.7% parameter reduction and a 9.4% inference speed increase while maintaining nearly unchanged accuracy, verifying the effectiveness of windowed models and lightweight attention. What are the implications of the main findings? It offers a favorable accuracy–efficiency trade-off for cloud segmentation under tight GPU memory and compute budgets, as quantified on a specified workstation-class GPU in the Results; embedded edge or on-board deployment is not experimentally validated here and is noted as future work, consistent with the Introduction; The model demonstrates strong generalization and robustness across multiple remote sensing datasets, providing critical empirical references for future research on efficient remote sensing segmentation architectures. Accurate cloud and cloud-shadow segmentation is a crucial step in optical remote sensing image preprocessing, playing a significant role in subsequent applications such as land-cover classification and change detection. However, the complexity of cloud/shadow shapes and noise interference (e.g., snow and ice, buildings, complex backgrounds, and atmospheric optics) make this task challenging. Although existing deep learning methods have achieved remarkable results in cloud segmentation tasks, a better balance between computational efficiency and segmentation accuracy is still needed. Traditional deep learning models have good detail and generalization capabilities due to their local feature extraction ability and spatial invariance, but they are relatively weak in processing global context information, leading to false positives and false negatives in complex scenarios. Encoders based on state space models (such as VMamba) can effectively capture global context through long-range dependency modeling, but there is still room for optimization in computational efficiency. Additionally, complex attention mechanisms (such as CBAM) can improve feature representation capability, but the large number of parameters limits the deployment efficiency of models. This paper conducts a systematic architectural exploration of the MCloudX cloud segmentation network, seeking a balance between efficiency and accuracy from three directions: backbone network modernization, encoder efficiency optimization, and attention mechanism lightweighting. Through comprehensive ablation experiments on SPARCS and L8-Biome datasets, we systematically evaluate the independent and synergistic effects of each component and validate them on Biome_3 and SPARCS datasets. Experimental results show that the proposed optimization configuration (ResNet50+LocalMamba+ECA-Net) significantly improves computational efficiency while maintaining comparable accuracy to the baseline. We name this optimization configuration LECloud, providing valuable empirical references for future research on efficient remote sensing segmentation architectures. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 20724292 |
| DOI: | 10.3390/rs18091341 |
