arXiv 2504.166652026-01-13cs.CV

一种面向遥感分类的差分注意力感知状态空间融合模型

A Diff-Attention Aware State Space Fusion Model for Remote Sensing Classification

Wenping Ma, Boyou Xue, Mengru Ma, Chuang Chen, Hekai Zhang, Hao Zhu

备注：: After a careful review, we discovered that there were data errors in the paper, which led to the invalidity of the conclusion. To avoid misleading the readers, we have decided to withdraw this article. We appreciate your understanding and support for our work

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出DAS2F-Model，通过差分注意力模块和线性融合模块提升多模态遥感图像分类性能。

摘要：

多光谱（MS）和全色（PAN）图像描述同一片土地表面，因此这些图像不仅有各自的优势，还有大量相似的信息。为了分离这些相似信息及其各自的优势，减少融合阶段的特征冗余。本文介绍了一种多模态遥感图像分类的差分注意力感知状态空间融合模型（DAS2F-Model）。基于选择性状态空间模型，设计了一个跨模态差分注意力模块（CMDA-Module），用于提取和分离MS和PAN图像的共同特征及其各自主导特征。其中，空间保留视觉Mamba（SPVM）通过合理优化视觉Mamba的输入来保留图像空间特征，并通过捕捉局部特征。考虑到在特征分离后，融合阶段的特征会有较大的语义差异，简单的融合操作难以有效整合这些显著不同的特征，因此提出了一种注意力感知线性融合模块（AALF-Module）。该模块通过计算影响系数进行像素级线性融合。这种机制可以在保持特征大小不变的情况下融合语义差异大的特征。实证评估表明，所提出的方法在性能上优于其他方法。相关代码可在：https://github.com/AVKSKVL/DAS-F-Model 获得。

英文摘要：

Multispectral (MS) and panchromatic (PAN) images describe the same land surface, so these images not only have their own advantages, but also have a lot of similar information. In order to separate these similar information and their respective advantages, reduce the feature redundancy in the fusion stage. This paper introduces a diff-attention aware state space fusion model (DAS2F-Model) for multimodal remote sensing image classification. Based on the selective state space model, a cross-modal diff-attention module (CMDA-Module) is designed to extract and separate the common features and their respective dominant features of MS and PAN images. Among this, space preserving visual mamba (SPVM) retains image spatial features and captures local features by optimizing visual mamba's input reasonably. Considering that features in the fusion stage will have large semantic differences after feature separation and simple fusion operations struggle to effectively integrate these significantly different features, an attention-aware linear fusion module (AALF-Module) is proposed. It performs pixel-wise linear fusion by calculating influence coefficients. This mechanism can fuse features with large semantic differences while keeping the feature size unchanged. Empirical evaluations indicate that the presented method achieves better results than alternative approaches. The relevant code can be found at:https://github.com/AVKSKVL/DAS-F-Model

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。