FEMNet: A Feature-Enriched Mamba Network for Cloud Detection in Remote Sensing Imagery
Accurate and efficient cloud detection is critical for maintaining the usability of optical remote sensing imagery, particularly in large-scale Earth observation systems. In this study, we propose FEMNet, a lightweight dual-branch network that combines state space modeling with convolutional encodin...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/15/2639 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849406450347016192 |
|---|---|
| author | Weixing Liu Bin Luo Jun Liu Han Nie Xin Su |
| author_facet | Weixing Liu Bin Luo Jun Liu Han Nie Xin Su |
| author_sort | Weixing Liu |
| collection | DOAJ |
| description | Accurate and efficient cloud detection is critical for maintaining the usability of optical remote sensing imagery, particularly in large-scale Earth observation systems. In this study, we propose FEMNet, a lightweight dual-branch network that combines state space modeling with convolutional encoding for multi-class cloud segmentation. The Mamba-based encoder captures long-range semantic dependencies with linear complexity, while a parallel CNN path preserves spatial detail. To address the semantic inconsistency across feature hierarchies and limited context perception in decoding, we introduce the following two targeted modules: a cross-stage semantic enhancement (CSSE) block that adaptively aligns low- and high-level features, and a multi-scale context aggregation (MSCA) block that integrates contextual cues at multiple resolutions. Extensive experiments on five benchmark datasets demonstrate that FEMNet achieves state-of-the-art performance across both binary and multi-class settings, while requiring only 4.4M parameters and 1.3G multiply–accumulate operations. These results highlight FEMNet’s suitability for resource-efficient deployment in real-world remote sensing applications. |
| format | Article |
| id | doaj-art-c6310c0848274b63b2c0594ccd16fcb8 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-c6310c0848274b63b2c0594ccd16fcb82025-08-20T03:36:22ZengMDPI AGRemote Sensing2072-42922025-07-011715263910.3390/rs17152639FEMNet: A Feature-Enriched Mamba Network for Cloud Detection in Remote Sensing ImageryWeixing Liu0Bin Luo1Jun Liu2Han Nie3Xin Su4State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, ChinaSchool of Artificial Intelligence, Wuhan University, Wuhan 430079, ChinaAccurate and efficient cloud detection is critical for maintaining the usability of optical remote sensing imagery, particularly in large-scale Earth observation systems. In this study, we propose FEMNet, a lightweight dual-branch network that combines state space modeling with convolutional encoding for multi-class cloud segmentation. The Mamba-based encoder captures long-range semantic dependencies with linear complexity, while a parallel CNN path preserves spatial detail. To address the semantic inconsistency across feature hierarchies and limited context perception in decoding, we introduce the following two targeted modules: a cross-stage semantic enhancement (CSSE) block that adaptively aligns low- and high-level features, and a multi-scale context aggregation (MSCA) block that integrates contextual cues at multiple resolutions. Extensive experiments on five benchmark datasets demonstrate that FEMNet achieves state-of-the-art performance across both binary and multi-class settings, while requiring only 4.4M parameters and 1.3G multiply–accumulate operations. These results highlight FEMNet’s suitability for resource-efficient deployment in real-world remote sensing applications.https://www.mdpi.com/2072-4292/17/15/2639cloud detectionremote sensing imageMambadeep learning |
| spellingShingle | Weixing Liu Bin Luo Jun Liu Han Nie Xin Su FEMNet: A Feature-Enriched Mamba Network for Cloud Detection in Remote Sensing Imagery Remote Sensing cloud detection remote sensing image Mamba deep learning |
| title | FEMNet: A Feature-Enriched Mamba Network for Cloud Detection in Remote Sensing Imagery |
| title_full | FEMNet: A Feature-Enriched Mamba Network for Cloud Detection in Remote Sensing Imagery |
| title_fullStr | FEMNet: A Feature-Enriched Mamba Network for Cloud Detection in Remote Sensing Imagery |
| title_full_unstemmed | FEMNet: A Feature-Enriched Mamba Network for Cloud Detection in Remote Sensing Imagery |
| title_short | FEMNet: A Feature-Enriched Mamba Network for Cloud Detection in Remote Sensing Imagery |
| title_sort | femnet a feature enriched mamba network for cloud detection in remote sensing imagery |
| topic | cloud detection remote sensing image Mamba deep learning |
| url | https://www.mdpi.com/2072-4292/17/15/2639 |
| work_keys_str_mv | AT weixingliu femnetafeatureenrichedmambanetworkforclouddetectioninremotesensingimagery AT binluo femnetafeatureenrichedmambanetworkforclouddetectioninremotesensingimagery AT junliu femnetafeatureenrichedmambanetworkforclouddetectioninremotesensingimagery AT hannie femnetafeatureenrichedmambanetworkforclouddetectioninremotesensingimagery AT xinsu femnetafeatureenrichedmambanetworkforclouddetectioninremotesensingimagery |