中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 中科院工业视觉智能装备工程实验室
  5. 精密感知与控制
Surface defect detection and semantic segmentation with a novel lightweight deep neural network

文献类型：期刊论文

作者Huang,Qiang1; Li,Fudong1; Yang,Yuequan1; Tao,Xian2,3; Li,Wei1; Wang,Xu4; Wang,Yong1
刊名Measurement Science and Technology
出版日期2024-05-22
卷号35期号:8页码:14
关键词deep learning surface defect detection semantic segmentation lightweight network
ISSN号0957-0233
DOI10.1088/1361-6501/ad4ab2
通讯作者Yang,Yuequan()
英文摘要Abstract Current approaches to defect detection and segmentation make essential use of machine learning methods. To develop lightweight models is one of key tasks for many defect detection and segmentation applications. In this work, we present a lightweight trilateral parallel feature extraction with multi-feature aggregation network (TriMFANet) for surface defect detection and segmentation. In TriMFANet, the top lateral is the feature-rich extraction used to capture detailed information. The other two laterals, efficient semantic feature extraction (ESFE) and reverse ESFE, leverage Hadamard product attention to jointly extract deep-level global feature information. Additionally, the MFA module employs origin-symmetric sigmoid attention to enhance deep feature information and integrates the triple features. We conducted binary defect segmentation tasks on the SD-saliency-900 and RSDDs datasets, achieving outstanding performance in both S α and E ξ . For multi-class defect detection tasks on the NEU-Seg and MSD datasets, we rank first with mIoU scores of 79.0% and 81.2% respectively. Experimental results demonstrate that our lightweight model with only 90 K parameters exhibits excellent performance.
资助项目Practice Innovation Program of Jiangsu Province[62073322] ; Practice Innovation Program of Jiangsu Province[62373350] ; National Natural Science Foundation of China[2023145] ; Youth Innovation Promotion Association CAS[GYY-ZNJS-2022-ZY-002-2-2022-002] ; Binzhou Institute of Technology[SJCX22_1712] ; Postgraduate Research & Practice Innovation Program of Jiangsu Province
WOS研究方向Engineering ; Instruments & Instrumentation
语种英语
WOS记录号IOP:MST_35_8_085017
出版者IOP Publishing
资助机构Practice Innovation Program of Jiangsu Province ; National Natural Science Foundation of China ; Youth Innovation Promotion Association CAS ; Binzhou Institute of Technology ; Postgraduate Research & Practice Innovation Program of Jiangsu Province
源URL[http://ir.ia.ac.cn/handle/173211/58307]  
专题精密感知与控制研究中心_精密感知与控制
通讯作者Yang,Yuequan
作者单位1.College of Information Engineering (College of Artificial Intelligence), Yangzhou University, Yangzhou 225009, People’s Republic of China
2.Institute of Automation, Chinese Academy of Sciences, Beijing 100190, People’s Republic of China
3.Binzhou Institute of Technology, Binzhou 256606, People’s Republic of China
4.Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area, Shenzhen Polytechnic University, Shenzhen 518055, People’s Republic of China
推荐引用方式
GB/T 7714		 Huang,Qiang,Li,Fudong,Yang,Yuequan,et al. Surface defect detection and semantic segmentation with a novel lightweight deep neural network[J]. Measurement Science and Technology,2024,35(8):14.
APA Huang,Qiang.,Li,Fudong.,Yang,Yuequan.,Tao,Xian.,Li,Wei.,...&Wang,Yong.(2024).Surface defect detection and semantic segmentation with a novel lightweight deep neural network.Measurement Science and Technology,35(8),14.
MLA Huang,Qiang,et al."Surface defect detection and semantic segmentation with a novel lightweight deep neural network".Measurement Science and Technology 35.8(2024):14.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。