信息与控制2025，Vol.54Issue(3)：502-512,11.DOI:10.13976/j.cnki.xk.2024.4085
基于小样本学习的表面缺陷检测方法
Surface Defect Detection Method Based on Few-shot Learning
摘要
Abstract
In intelligent industrial production,defect detection technology using deep learning faces challenges such as insufficient defect samples,different defect sizes,and low detection accuracy.To address these problems,we propose a surface defect detection model leveraging few-shot learn-ing,building on the Faster R-CNN(Faster Region-based Convolutional Neural Network).First,we enhance the traditional convolution in the ResNet101 and FPN(Feature Pyramid Network)backbone network with deformable convolutions to extract features.Objects are then extracted from images to generate an object pyramid,selecting corresponding features as positive samples to en-rich the scale space of small samples.Finally,we encode RoI(Region of Interest)features using contrastive learning to measure the similarity between regional proposals,achieving a more compact feature representation and reducing misclassification issues in small samples.Finally,comparative experiments on the collected small sample defect dataset demonstrate the model's effectiveness,yielding a 96.6％accuracy and 70.6％average accuracy,outperforming other models.关键词
小样本学习/表面缺陷检测/可变形卷积/目标金字塔/对比学习Key words
few-shot learning/surface defect detection/deformable convolution/object pyramid/contrastive learning分类
计算机与自动化引用本文复制引用
苏奕铭,贺睿杰,刘雅静,田建东..基于小样本学习的表面缺陷检测方法[J].信息与控制,2025,54(3):502-512,11.基金项目
国家自然科学基金项目(U2013210) （U2013210）
中国科学院青年创新促进会项目(2019000399) （2019000399）
