东北大学学报(自然科学版) ›› 2024, Vol. 45 ›› Issue (3): 354-360.DOI: 10.12068/j.issn.1005-3026.2024.03.007

• 机械工程 • 上一篇    下一篇

基于元学习的带钢表面缺陷小样本语义分割

冯虎, 宋克臣(), 崔文琦, 颜云辉   

  1. 东北大学 机械工程与自动化学院,辽宁 沈阳 110819
  • 收稿日期:2022-10-21 出版日期:2024-03-15 发布日期:2024-05-17
  • 通讯作者: 宋克臣
  • 作者简介:冯 虎(1998-),男,陕西汉中人,东北大学硕士研究生
    颜云辉(1960-),男,江苏丹阳人,东北大学教授,博士生导师.
  • 基金资助:
    国家自然科学基金资助项目(51805078);中央高校基本科研业务费专项资金资助项目(N2103011)

Few-Shot Semantic Segmentation of Strip Steel Surface Defects Based on Meta-Learning

Hu FENG, Ke-chen SONG(), Wen-qi CUI, Yun-hui YAN   

  1. School of Mechanical Engineering & Automation,Northeastern University,Shenyang 110819,China.
  • Received:2022-10-21 Online:2024-03-15 Published:2024-05-17
  • Contact: Ke-chen SONG
  • About author:SONG Ke-chen, E-mail: songkc@me.neu.edu.cn

摘要:

由于缺少带钢表面缺陷样本,使得深度神经网络在带钢表面缺陷检测的应用受到了限制,为解决这一实际问题,提出了一种基于元学习思想的小样本语义分割深度学习方法.该方法引入了多尺度解码器和注意力机制.多尺度解码器能够聚合不同尺度的缺陷特征信息,提高网络的分割精度.注意力机制能够有效增强缺陷信息表达,并且抑制背景信息的干扰.此外,构建了一个带钢表面缺陷语义分割数据集,该数据集包含9类带钢表面缺陷.在该数据集上进行了相关实验,结果表明本文方法在平均交并比和前景-背景交并比指标上优于PFENet,SCLNet和HSNet等方法.

关键词: 带钢表面缺陷检测, 元学习, 小样本语义分割, 注意力机制, 多尺度解码器

Abstract:

Due to the limited availability of strip surface defect samples, the application of deep neural networks in strip surface detection is constrained. To solve this practical issue, a meta‐learning‐based few‐shot semantic segmentation method is proposed. A multi‐scale decoder and attention mechanism are used in the proposed method. The multi‐scale decoder can aggregate the defect information at different scales and improve segmentation accuracy of the proposed network. The attention mechanism can effectively improve the expression of defect features and suppress the interference of defect background information. In addition, a novel few‐shot steel strip surface defect semantic segmentation dataset is constructed including nine classes of strip steel surface defects. Comparison experiments on the proposed dataset show that the proposed method is superior to similar few‐shot segmentation methods such as PFENet, SCLNet, and HSNet in terms of evaluation index mean intersection over union and foreground‐background intersection over union.

Key words: strip steel surface defect detection, meta‐learning, few‐shot semantic segmentation, attention mechanism, multi‐scale decoder

中图分类号: