Sparse-MoE-SAM: A Lightweight Framework Integrating MoE and SAM with a Sparse Attention Mechanism for Plant Disease Segmentation in Resource-Constrained Environments

认领

导出

Link by DOI

反馈

作者信息关键词期刊信息基础信息归属信息摘要

成果类型：

期刊论文

作者：

Zhao, Benhan;Kang, Xilin;Zhou, Hao;Shi, Ziyang;Li, Lin*;...

通讯作者：

Li, Lin;Zhou, GX

作者机构：

[Zhao, Benhan; Zhou, Hao; Yan, Yongming; Li, Lin; Shi, Ziyang; Wan, Fangying; Zhu, Jiangzhang; Zhou, Guoxiong] Cent South Univ Forestry & Technol, Sch Elect Informat & Phys, Changsha 410004, Peoples R China.

[Kang, Xilin] Jiangsu Univ Sci & Technol, Sch Comp, Zhenjiang 212100, Peoples R China.

[Li, Leheng] Cent South Univ Forestry & Technol, Sch Forestry, Changsha 410004, Peoples R China.

[Wu, Yulong] Cent South Univ Forestry & Technol, Bangor Coll, Changsha 410004, Peoples R China.

通讯机构：

[Li, L; Zhou, GX ] C

Cent South Univ Forestry & Technol, Sch Elect Informat & Phys, Changsha 410004, Peoples R China.

语种：

英文

关键词：

plant disease segmentation;sparse attention;mixture of experts;SAM (Segment Anything Model)

期刊：

Plants-Basel

ISSN：

2223-7747

年：

2025

卷：

期：

页码：

DOI：

10.3390/plants14172634

基金类别：

National Natural Science Foundation in China; Education Department Key Program of Hunan Province [21A0160]; [61902436]

机构署名：

本校为第一且通讯机构

院系归属：

林学院

班戈学院

摘要：

Plant disease segmentation has achieved significant progress with the help of artificial intelligence. However, deploying high-accuracy segmentation models in resource-limited settings faces three key challenges, as follows: (A) Traditional dense attention mechanisms incur quadratic computational complexity growth (O(n2d)), rendering them ill-suited for low-power hardware. (B) Naturally sparse spatial distributions and large-scale variations in the lesions on leaves necessitate models that concurrently capture long-range dependencies and local details. (C) Complex backgrounds and variable ligh...

反馈

产权有误：本人成果被他人认领

数据有误：数据基本信息有误

归属有误：成果的院系归属、机构署名归属有误

其他原因：

验证码：

看不清楚，换一个

确定

取消

成果认领

标题：

用户	作者	通讯作者	--
	请选择	请选择	--

确定

取消

Sparse-MoE-SAM: A Lightweight Framework Integrating MoE and SAM with a Sparse Attention Mechanism for Plant Disease Segmentation in Resource-Constrained Environments

反馈

成果认领

提示

该栏目需要登录且有访问权限才可以访问