桂林电子科技大学学报2026，Vol.46Issue(1)：10-19,10.DOI:10.16725/j.1673-808X.2025148
缺陷检测中小样本问题的研究进展
Research progress on small-sample problem in defect detection
摘要
Abstract
In modern industrial defect detection,deep learning methods have been widely applied but are often limited by the small-sample problem.Addressing this issue can improve detection accuracy and efficiency,reduce technical barrier,and enable small and medium-sized enterprises to lower costs and improve productivity.This paper first defines the small-sample problem and discusses its implications,then reviews the current research,analyzes the advantages and limitations of representative methods and their appli-cable scenarios,and compares costs and feasibility to offer practical guidance.Finally,future research directions and potential solu-tions are discussed,aiming to provide theoretical and practical references for addressing the small-sample problem in defect detec-tion and promoting further development and application in this field.关键词
缺陷检测/小样本/深度学习/数据增强/迁移学习/度量学习/元学习Key words
defect detection/small sample/deep learning/data augmentation/transfer learning/metric learning/meta-learning分类
信息技术与安全科学引用本文复制引用
童金武,王希,邓明洋,沈嘉毅,唐文轩,沙守富,黄紫杰,刘艳红..缺陷检测中小样本问题的研究进展[J].桂林电子科技大学学报,2026,46(1):10-19,10.基金项目
教育部微惯性仪器与先进导航技术重点实验室基金(SEU-MIAN-202102) （SEU-MIAN-202102）
南京工程学院人才引进科研启动基金(YKJ202043) （YKJ202043）
南京市卫生科技发展重大项目(ZDX22001) （ZDX22001）
江苏省卫生健康发展研究中心开放课题(JSHD2021017) （JSHD2021017）
江苏省大学生创新创业训练计划(202311276120Y,202411276102Y,202412276107Y,20241276121Y) （202311276120Y,202411276102Y,202412276107Y,20241276121Y）
