MSCloudCAM: Multi-Scale Context Adaptation with Convolutional Cross-Attention for Multispectral Cloud Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mazid, Md Abdullah Al, Deng, Liangdong, Rishe, Naphtali
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918307092758528
author Mazid, Md Abdullah Al
Deng, Liangdong
Rishe, Naphtali
author_facet Mazid, Md Abdullah Al
Deng, Liangdong
Rishe, Naphtali
contents Clouds remain a major obstacle in optical satellite imaging, limiting accurate environmental and climate analysis. To address the strong spectral variability and the large scale differences among cloud types, we propose MSCloudCAM, a novel multi-scale context adapter network with convolution based cross-attention tailored for multispectral and multi-sensor cloud segmentation. A key contribution of MSCloudCAM is the explicit modeling of multiple complementary multi-scale context extractors. And also, rather than simply stacking or concatenating their outputs, our formulation uses one extractor's fine-resolution features and the other extractor's global contextual representations enabling dynamic, scale-aware feature selection. Building on this idea, we design a new convolution-based cross attention adapter that effectively fuses localized, detailed information with broader multi-scale context. Integrated with a hierarchical vision backbone and refined through channel and spatial attention mechanisms, MSCloudCAM achieves strong spectral-spatial discrimination. Experiments on various multisensor datatsets e.g. CloudSEN12 (Sentinel-2) and L8Biome (Landsat-8), demonstrate that MSCloudCAM achieves superior overall segmentation performance and competitive class-wise accuracy compared to recent state-of-the-art models, while maintaining competitive model complexity, highlighting the novelty and effectiveness of the proposed design for large-scale Earth observation.
format Preprint
id arxiv_https___arxiv_org_abs_2510_10802
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MSCloudCAM: Multi-Scale Context Adaptation with Convolutional Cross-Attention for Multispectral Cloud Segmentation
Mazid, Md Abdullah Al
Deng, Liangdong
Rishe, Naphtali
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
F.2.2; I.2.7
Clouds remain a major obstacle in optical satellite imaging, limiting accurate environmental and climate analysis. To address the strong spectral variability and the large scale differences among cloud types, we propose MSCloudCAM, a novel multi-scale context adapter network with convolution based cross-attention tailored for multispectral and multi-sensor cloud segmentation. A key contribution of MSCloudCAM is the explicit modeling of multiple complementary multi-scale context extractors. And also, rather than simply stacking or concatenating their outputs, our formulation uses one extractor's fine-resolution features and the other extractor's global contextual representations enabling dynamic, scale-aware feature selection. Building on this idea, we design a new convolution-based cross attention adapter that effectively fuses localized, detailed information with broader multi-scale context. Integrated with a hierarchical vision backbone and refined through channel and spatial attention mechanisms, MSCloudCAM achieves strong spectral-spatial discrimination. Experiments on various multisensor datatsets e.g. CloudSEN12 (Sentinel-2) and L8Biome (Landsat-8), demonstrate that MSCloudCAM achieves superior overall segmentation performance and competitive class-wise accuracy compared to recent state-of-the-art models, while maintaining competitive model complexity, highlighting the novelty and effectiveness of the proposed design for large-scale Earth observation.
title MSCloudCAM: Multi-Scale Context Adaptation with Convolutional Cross-Attention for Multispectral Cloud Segmentation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
F.2.2; I.2.7
url https://arxiv.org/abs/2510.10802