版权说明 操作指南
首页 > 成果 > 详情

ASTKD-PCB-LDD: high-performance PCB defect detection model with align soft-target knowledge distillation and lightweight network design

认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Hu, Zhelun;Zhang, Zhao;Liu, Shenbo;Zhao, Dongxue;Zheng, Longhao;...
通讯作者:
Tang, LJ
作者机构:
[Zhao, Dongxue; Tang, Lijun; Zheng, Longhao; Liu, Shenbo; Hu, Zhelun; Tang, LJ; Zhang, Zhao] Changsha Univ Sci & Technol, Sch Phys & Elect Sci, 960th Wanjiali St, Changsha 410114, Hunan, Peoples R China.
通讯机构:
[Tang, LJ ] C
Changsha Univ Sci & Technol, Sch Phys & Elect Sci, 960th Wanjiali St, Changsha 410114, Hunan, Peoples R China.
语种:
英文
关键词:
PCB defect detection;Deep learning;Knowledge distillation;Model pruning
期刊:
JOURNAL OF SUPERCOMPUTING
ISSN:
0920-8542
年:
2025
卷:
81
期:
4
页码:
1-23
基金类别:
This work was supported by the Key Projects for Postgraduate Students of Hunan Provincial Department of Education (No. CX20210742).
机构署名:
本校为第一且通讯机构
院系归属:
物理与电子科学学院
摘要:
Defects in printed circuit boards (PCBs) can degrade the performance and reliability of electronic devices. Although YOLOv5-based algorithms are commonly used to detect PCB defects, their complex parameters slow down detection speeds on industrial platforms. This paper presents a lightweight, high-performance model for PCB defect detection, called Align Soft-Target Knowledge Distillation PCB Lightweight Defect Detection (ASTKD-PCB-LDD). The model uses the k-means++ algorithm for optimal anchor box selection and the SCYLLA-IoU (SIoU) loss function to improve accuracy in detecting small defects....

反馈

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

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com