arXiv 2405.105302024-05-17cs.CV

CM-UNet: 用于遥感图像语义分割的混合CNN-Mamba UNet

CM-UNet: Hybrid CNN-Mamba UNet for Remote Sensing Image Semantic Segmentation

College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息与电子工程学院）；School of Aeronautics and Astronautics, Zhejiang University（浙江大学航空航天学院）；College of Computer Science, Zhejiang University（浙江大学计算机学院）

Mushui Liu, Jun Dan, Ziqian Lu, Yunlong Yu, Yingming Li, Xi Li

备注：: 5 pages, 6 figures

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对现有遥感图像语义分割方法长程依赖捕获不足或计算复杂的问题，提出融合CNN编码器与Mamba解码器的CM-UNet，通过CSMamba模块和MSAA模块增强特征融合，在三个基准上性能优于现有方法。

摘要：

由于遥感图像尺寸大且目标存在变化，当前基于CNN和基于Transformer的遥感图像语义分割方法在捕获长程依赖方面效果欠佳，或是受限于复杂的计算复杂度。本文提出CM-UNet，它包含一个用于提取局部图像特征的基于CNN的编码器，以及一个用于聚合与整合全局信息的基于Mamba的解码器，可实现高效的遥感图像语义分割。具体而言，我们引入了CSMamba模块来构建核心分割解码器，该模块将通道注意力与空间注意力作为原生Mamba的门控激活条件，以增强特征交互与全局-局部信息融合。此外，为进一步优化CNN编码器输出的特征，我们采用多尺度注意力聚合（Multi-Scale Attention Aggregation, MSAA）模块来融合不同尺度的特征。通过整合CSMamba模块与MSAA模块，CM-UNet能够有效捕获大尺寸遥感图像的长程依赖与多尺度全局上下文信息。在三个基准数据集上的实验结果表明，所提出的CM-UNet在各项性能指标上均优于现有方法。代码可在https://github.com/XiaoBuL/CM-UNet获取。

英文摘要：

Due to the large-scale image size and object variations, current CNN-based and Transformer-based approaches for remote sensing image semantic segmentation are suboptimal for capturing the long-range dependency or limited to the complex computational complexity. In this paper, we propose CM-UNet, comprising a CNN-based encoder for extracting local image features and a Mamba-based decoder for aggregating and integrating global information, facilitating efficient semantic segmentation of remote sensing images. Specifically, a CSMamba block is introduced to build the core segmentation decoder, which employs channel and spatial attention as the gate activation condition of the vanilla Mamba to enhance the feature interaction and global-local information fusion. Moreover, to further refine the output features from the CNN encoder, a Multi-Scale Attention Aggregation (MSAA) module is employed to merge the different scale features. By integrating the CSMamba block and MSAA module, CM-UNet effectively captures the long-range dependencies and multi-scale global contextual information of large-scale remote-sensing images. Experimental results obtained on three benchmarks indicate that the proposed CM-UNet outperforms existing methods in various performance metrics. The codes are available at https://github.com/XiaoBuL/CM-UNet.

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。