自动化与信息工程2026，Vol.47Issue(4)：17-25,9.DOI:10.12475/aie.20260403
多尺度自监督特征融合的工业视觉缺陷检测方法
Multi-scale Self-supervised Feature Fusion Method for Industrial Visual Defect Detection
摘要
Abstract
Aiming at the problem that visual defect detection models require retraining and parameter tuning after product category switching,we propose an industrial visual defect detection method based on multi-scale self-supervised feature fusion.The method employs a frozen self-supervised visual backbone network to extract shallow,middle,and deep patch token features in parallel via multiple hooks,and hierarchically constructs a core subset memory bank for each layer.It then fuses the nearest neighbor distances from all layers into a unified anomaly map using an equal-weight score-level fusion mechanism,thereby avoiding category-wise parameter tuning and retraining.On all 15 categories of the MVTec-AD dataset under 3 random seeds,the image-level AUROC reaches 0.987 4±0.001 7,with a cross-seed standard deviation that is only 11％-20％of that of the same backbone baseline,while the region-level PRO achieves 0.816 3±0.012 1.Ablation study results attribute the reduction in cross-seed standard deviation primarily to the equal-weight score-level fusion mechanism of multiple hooks;the standard deviation reduction of multi-layer compared to single-layer L9 across all 15 categories is approximately 45％.When zero-shot transferred to all 12 categories of the VisA dataset,the P-AUROC reaches 0.992 9;on the first 6 categories of the Real-IAD dataset,the P-AUROC achieves 0.984 7.On a self-collected engine cylinder liner defect image dataset,the P-AUROC reaches 0.967 3±0.001 5.In half-precision mode,the inference time per image is about 25 ms,which can meet the takt time requirements of typical medium-speed production lines.关键词
工业视觉/缺陷检测/自监督学习/多尺度特征/零样本迁移Key words
industrial visual/anomaly detection/self-supervised learning/multi-scale features/zero-shot transfer分类
信息技术与安全科学引用本文复制引用
陈永彬,黄嘉思,黄国健..多尺度自监督特征融合的工业视觉缺陷检测方法[J].自动化与信息工程,2026,47(4):17-25,9.基金项目
广州市青年科技人才托举工程项目(QT-2025-010) （QT-2025-010）
