郑州大学学报（工学版）2025，Vol.46Issue(5)：69-76,8.DOI:10.13705/j.issn.1671-6833.2025.05.009
基于Transformer多元注意力的钢材表面缺陷视觉检测
Visual Detection of Steel Surface Defects Based on Transformer and Multi-attention
摘要
Abstract
Addressing the challenges posed by the varying scales of steel surface defects and the limited multi-scale feature processing capabilitied and accuracy of existing detection algorithms,in this study a steel surface defect de-tection method that integrates hybrid sampling and multi-attention collaboration was proposed.Firstly,an efficient channel feature extraction backbone was constructed to emphasize defect feature extraction against the complex background of steel surfaces.Secondly,a dual-attention collaborative feature pyramid was introduced to expand the network's receptive field,thereby enhancing the capture of multi-scale defect features and improving the detection performance for small targets.Finally,a Transformer-based hybrid sampling strategy was designed to dynamically perceive defect regions,thereby boosting the overall detection performance of the model.Experimental comparisons on the NEU-DET dataset revealed that,compared to the baseline DETR algorithm,the improved algorithm achieved a 6.1 percentage point increase in mean average precision,reaching 81.4%,thereby enhancing the model's accu-racy in detecting steel surface defects.Additionally,with a detection speed of 44.2 frame/s,the proposed algo-rithm strikes a commendable balance between detection speed and performance.关键词
缺陷检测/注意力机制/Transformer/混合采样/DETRKey words
defect detection/attention mechanism/Transformer/hybrid sampling/DETR分类
信息技术与安全科学引用本文复制引用
韩慧健,邢怀宇,张云峰,张锐..基于Transformer多元注意力的钢材表面缺陷视觉检测[J].郑州大学学报（工学版）,2025,46(5):69-76,8.基金项目
国家自然科学基金资助项目(61972227) （61972227）
山东省自然科学基金青年基金资助项目(ZR2023QF161) （ZR2023QF161）
