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. 多模态人工智能系统全国重点实验室
Attention-Based Multiscale Feature Fusion for Efficient Surface Defect Detection

文献类型：期刊论文

作者Zhao, Yuhao1; Liu, Qing2; Su, Hu3; Zhang, Jiabin4; Ma, Hongxuan3; Zou, Wei3; Liu, Song1,5
刊名IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
出版日期2024
卷号73页码:10
关键词Attention mechanism feature enhancement feature fusion object detection surface defect detection
ISSN号0018-9456
DOI10.1109/TIM.2024.3372229
通讯作者Zou, Wei(wei.zou@ia.ac.cn) ; Liu, Song(liusong@shanghaitech.edu.cn)
英文摘要Deep-learning-based detection methods have been widely applied to industrial defect inspection. However, directly using vanilla detection methods fails to achieve satisfying performance due to the lack of identifiable features. In this article, a novel attention-based multiscale feature fusion module (AMFF) is proposed, aiming to enhance defect features and improve defect identification by leveraging attention mechanism in the feature fusion. AMFF includes self-enhanced attention module (SEAM) and cross-enhanced attention module (CEAM). SEAM is performed on a single feature map, which first adopts multiple dilation convolutions to enrich contextual information without compromising resolution and then utilizes the intralayer attention on the current feature map. CEAM takes both the current feature map and the adjacent feature map as input to perform cross-layer attention. The adjacent feature map is modulated with the guidance of the current feature map, which is then combined with the current feature map and the output of SEAM for final prediction. AMFF is utilized in current feature fusion networks, e.g., feature pyramid network (FPN) and path aggregation FPN (PAFPN), and is further integrated into prevalent detectors to guide them to pay more attention to defects rather than the background. Extensive experiments are conducted on two real industrial datasets released by Tianchi platform, i.e., fabric and aluminum defect datasets. For each dataset, 500 images are randomly selected for test and the rest for training. The proposed AMFF is demonstrated to significantly boost defect detection accuracy with acceptable computational cost, and the real-time performance could fully satisfy practical requirements.
资助项目National Key Research and Development Program of China
WOS研究方向Engineering ; Instruments & Instrumentation
语种英语
WOS记录号WOS:001188560600008
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Key Research and Development Program of China
源URL[http://ir.ia.ac.cn/handle/173211/57999]  
专题多模态人工智能系统全国重点实验室
通讯作者Zou, Wei; Liu, Song
作者单位1.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China
2.Shanghai Tech Univ, Sch Informat Sci & Technol, Shanghai 201210, Peoples R China
3.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China
4.Alibaba Grp Taobao Co Ltd, Hangzhou 311121, Peoples R China
5.Shanghai Engn Res Ctr Intelligent Vis & Imaging, Shanghai 200050, Peoples R China
推荐引用方式
GB/T 7714		 Zhao, Yuhao,Liu, Qing,Su, Hu,et al. Attention-Based Multiscale Feature Fusion for Efficient Surface Defect Detection[J]. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT,2024,73:10.
APA Zhao, Yuhao.,Liu, Qing.,Su, Hu.,Zhang, Jiabin.,Ma, Hongxuan.,...&Liu, Song.(2024).Attention-Based Multiscale Feature Fusion for Efficient Surface Defect Detection.IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT,73,10.
MLA Zhao, Yuhao,et al."Attention-Based Multiscale Feature Fusion for Efficient Surface Defect Detection".IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 73(2024):10.

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。