PPMamba:基于金字塔池化局部辅助 SSM 模型的遥感图像语义分割技术

Yin Hu, Xianping Ma, Jialu Sui, Man-On Pun
{"title":"PPMamba:基于金字塔池化局部辅助 SSM 模型的遥感图像语义分割技术","authors":"Yin Hu, Xianping Ma, Jialu Sui, Man-On Pun","doi":"arxiv-2409.06309","DOIUrl":null,"url":null,"abstract":"Semantic segmentation is a vital task in the field of remote sensing (RS).\nHowever, conventional convolutional neural network (CNN) and transformer-based\nmodels face limitations in capturing long-range dependencies or are often\ncomputationally intensive. Recently, an advanced state space model (SSM),\nnamely Mamba, was introduced, offering linear computational complexity while\neffectively establishing long-distance dependencies. Despite their advantages,\nMamba-based methods encounter challenges in preserving local semantic\ninformation. To cope with these challenges, this paper proposes a novel network\ncalled Pyramid Pooling Mamba (PPMamba), which integrates CNN and Mamba for RS\nsemantic segmentation tasks. The core structure of PPMamba, the Pyramid\nPooling-State Space Model (PP-SSM) block, combines a local auxiliary mechanism\nwith an omnidirectional state space model (OSS) that selectively scans feature\nmaps from eight directions, capturing comprehensive feature information.\nAdditionally, the auxiliary mechanism includes pyramid-shaped convolutional\nbranches designed to extract features at multiple scales. Extensive experiments\non two widely-used datasets, ISPRS Vaihingen and LoveDA Urban, demonstrate that\nPPMamba achieves competitive performance compared to state-of-the-art models.","PeriodicalId":501289,"journal":{"name":"arXiv - EE - Image and Video Processing","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"PPMamba: A Pyramid Pooling Local Auxiliary SSM-Based Model for Remote Sensing Image Semantic Segmentation\",\"authors\":\"Yin Hu, Xianping Ma, Jialu Sui, Man-On Pun\",\"doi\":\"arxiv-2409.06309\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Semantic segmentation is a vital task in the field of remote sensing (RS).\\nHowever, conventional convolutional neural network (CNN) and transformer-based\\nmodels face limitations in capturing long-range dependencies or are often\\ncomputationally intensive. Recently, an advanced state space model (SSM),\\nnamely Mamba, was introduced, offering linear computational complexity while\\neffectively establishing long-distance dependencies. Despite their advantages,\\nMamba-based methods encounter challenges in preserving local semantic\\ninformation. To cope with these challenges, this paper proposes a novel network\\ncalled Pyramid Pooling Mamba (PPMamba), which integrates CNN and Mamba for RS\\nsemantic segmentation tasks. The core structure of PPMamba, the Pyramid\\nPooling-State Space Model (PP-SSM) block, combines a local auxiliary mechanism\\nwith an omnidirectional state space model (OSS) that selectively scans feature\\nmaps from eight directions, capturing comprehensive feature information.\\nAdditionally, the auxiliary mechanism includes pyramid-shaped convolutional\\nbranches designed to extract features at multiple scales. Extensive experiments\\non two widely-used datasets, ISPRS Vaihingen and LoveDA Urban, demonstrate that\\nPPMamba achieves competitive performance compared to state-of-the-art models.\",\"PeriodicalId\":501289,\"journal\":{\"name\":\"arXiv - EE - Image and Video Processing\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - EE - Image and Video Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.06309\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - EE - Image and Video Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.06309","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

语义分割是遥感(RS)领域的一项重要任务。然而,传统的卷积神经网络(CNN)和基于变压器的模型在捕捉远距离依赖关系方面存在局限性,而且往往计算量很大。最近,一种先进的状态空间模型(SSM),即 Mamba 被引入,它具有线性计算复杂度,同时能有效地建立长距离依赖关系。基于 Mamba 的方法尽管有其优势,但在保留局部语义信息方面却遇到了挑战。为了应对这些挑战,本文提出了一种称为金字塔池化 Mamba(PPMamba)的新型网络,它集成了 CNN 和 Mamba,可用于 RS 语义分割任务。PPMamba 的核心结构是金字塔池化状态空间模型(PP-SSM)块,它将局部辅助机制与全向状态空间模型(OSS)结合在一起,后者可选择性地从八个方向扫描特征图,从而捕获全面的特征信息。在 ISPRS Vaihingen 和 LoveDA Urban 这两个广泛使用的数据集上进行的大量实验表明,与最先进的模型相比,PPMamba 的性能极具竞争力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
PPMamba: A Pyramid Pooling Local Auxiliary SSM-Based Model for Remote Sensing Image Semantic Segmentation
Semantic segmentation is a vital task in the field of remote sensing (RS). However, conventional convolutional neural network (CNN) and transformer-based models face limitations in capturing long-range dependencies or are often computationally intensive. Recently, an advanced state space model (SSM), namely Mamba, was introduced, offering linear computational complexity while effectively establishing long-distance dependencies. Despite their advantages, Mamba-based methods encounter challenges in preserving local semantic information. To cope with these challenges, this paper proposes a novel network called Pyramid Pooling Mamba (PPMamba), which integrates CNN and Mamba for RS semantic segmentation tasks. The core structure of PPMamba, the Pyramid Pooling-State Space Model (PP-SSM) block, combines a local auxiliary mechanism with an omnidirectional state space model (OSS) that selectively scans feature maps from eight directions, capturing comprehensive feature information. Additionally, the auxiliary mechanism includes pyramid-shaped convolutional branches designed to extract features at multiple scales. Extensive experiments on two widely-used datasets, ISPRS Vaihingen and LoveDA Urban, demonstrate that PPMamba achieves competitive performance compared to state-of-the-art models.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信