信阳师范大学学报（自然科学版）2026，Vol.39Issue(1)：46-51,6.DOI:10.3969/j.issn.2097-583X.2026.01.006
基于增强可变形卷积的带钢表面缺陷检测网络
Strip steel surface defect detection network based on enhanced deformable convolution
摘要
Abstract
A novel network architecture for strip steel surface defect detection was proposed,which designed an enhanced deformable convolution module based on co-attention mechanism and integrated it into the backbone network as a plugin.By leveraging the co-attention mechanism,the shape of the convolution kernel was adaptively adjusted,which effectively captured irregular defects on the strip steel surface,and significantly improved the feature extraction capability of the backbone network.Experimental results on the NEU-DET dataset demonstrated that the proposed method achieved an average precision(mAP)of 81.6%.关键词
缺陷检测/可变形卷积/协同注意力Key words
defect detection/deformable convolution/collaborative attention分类
信息技术与安全科学引用本文复制引用
孙艳歌,徐成龙,郭华平,张莉..基于增强可变形卷积的带钢表面缺陷检测网络[J].信阳师范大学学报（自然科学版）,2026,39(1):46-51,6.基金项目
国家自然科学基金项目(62062004) （62062004）
河南省自然科学基金项目(222300420274) （222300420274）
信阳师范学院研究生科研创新基金项目(2021KYJJ56) （2021KYJJ56）
