HyperSMamba: A Lightweight Mamba for Efficient Hyperspectral Image Classification

高光谱成像 计算机科学 遥感 人工智能 计算机视觉 地质学
作者
Mengyuan Sun,Liejun Wang,Shaochen Jiang,Shuli Cheng,Lihan Tang
出处
期刊:Remote Sensing [Multidisciplinary Digital Publishing Institute]
卷期号:17 (12): 2008-2008 被引量:5
标识
DOI:10.3390/rs17122008
摘要

Deep learning has recently achieved remarkable progress in hyperspectral image (HSI) classification. Among these advancements, the Transformer-based models have gained considerable attention due to their ability to establish long-range dependencies. However, the quadratic computational complexity of the self-attention mechanism limits its application in hyperspectral image classification (HSIC). Recently, the Mamba architecture has shown outstanding performance in 1D sequence modeling tasks owing to its lightweight linear sequence operations and efficient parallel scanning capabilities. Nevertheless, its application in HSI classification still faces challenges. Most existing Mamba-based approaches adopt various selective scanning strategies for HSI serialization, ensuring the adjacency of scanning sequences to enhance spatial continuity. However, these methods lead to substantially increased computational overhead. To overcome these challenges, this study proposes the Hyperspectral Spatial Mamba (HyperSMamba) model for HSIC, aiming to reduce computational complexity while improving classification performance. The suggested framework consists of the following key components: (1) a Multi-Scale Spatial Mamba (MS-Mamba) encoder, which refines the state-space model (SSM) computation by incorporating a Multi-Scale State Fusion Module (MSFM) after the state transition equations of original SSMs. This module aggregates adjacent state representations to reinforce spatial dependencies among local features; (2) our proposed Adaptive Fusion Attention Module (AFAttention) to dynamically fuse bidirectional Mamba outputs for optimizing feature representation. Experiments were performed on three HSI datasets, and the findings demonstrate that HyperSMamba attains overall accuracy of 94.86%, 97.72%, and 97.38% on the Indian Pines, Pavia University, and Salinas datasets, while maintaining low computational complexity. These results confirm the model’s effectiveness and potential for practical application in HSIC tasks.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
wu完成签到 ,获得积分10
3秒前
JamesPei的应助被Vincent采纳,获得10
3秒前
苹果元灵完成签到,获得积分10
4秒前
4秒前
666666神花露水完成签到 ,获得积分10
7秒前
NexusExplorer的应助被Vincent采纳,获得10
10秒前
10秒前
yu完成签到 ,获得积分10
11秒前
17秒前
爆米花的应助被Vincent采纳,获得10
19秒前
23秒前
HAPPY完成签到,获得积分10
24秒前
桐桐的应助被Vincent采纳,获得10
25秒前
keleboys完成签到 ,获得积分10
27秒前
HMZ完成签到 ,获得积分10
29秒前
30秒前
HU完成签到 ,获得积分10
32秒前
33秒前
37秒前
小尾巴完成签到 ,获得积分10
40秒前
章鱼行者完成签到,获得积分10
40秒前
鲁文杰发布了新的文献求助10
41秒前
Maestro_S的应助被Vincent采纳,获得10
43秒前
44秒前
万能图书馆的应助被Vincent采纳,获得10
50秒前
50秒前
水静完成签到,获得积分10
51秒前
川川完成签到 ,获得积分10
55秒前
56秒前
科研通AI6.4的应助被Vincent采纳,获得10
56秒前
57秒前
标致访旋完成签到,获得积分10
58秒前
烂漫墨镜完成签到 ,获得积分10
1分钟前
20230054发布了新的文献求助10
1分钟前
1分钟前
隐形曼青的应助被Vincent采纳,获得10
1分钟前
鲁文杰完成签到,获得积分10
1分钟前
1分钟前
整齐百褶裙完成签到 ,获得积分10
1分钟前
Changhiwi完成签到 ,获得积分10
1分钟前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 2000
Sex, Aging, and Death in a Medieval Medical Compendium: Trinity College Cambridge MS R.14.52, Its Texts, Language, and Scribe 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
基于界面调控的高效湿气发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8190366
求助须知:如何正确求助?哪些是违规求助? 9577437
关于积分的说明 21852521
捐赠科研通 7788988
什么是DOI,文献DOI怎么找? 3436315
关于科研通互助平台的介绍 2560144
邀请新用户注册赠送积分活动 2482995