北京交通大学学报2025，Vol.49Issue(3)：14-22,9.DOI:10.11860/j.issn.1673-0291.20240062
基于通用视觉大模型与注意力增强的无监督异常检测
Unsupervised anomaly detection based on universal visual transformer and attention enhancement
摘要
Abstract
To address the common issues in existing unsupervised anomaly detection methods,such as insufficient feature extraction and the inability to effectively focus on anomalous regions,which lead to degraded detection performance,we propose an unsupervised anomaly detection method based on a general vision model and attention enhancement.First,the proposed method utilizes a pre-trained general vision model,the Vision Transformer(ViT),to extract features from input images.Second,to further enhance the model's focus on abnormal regions,we incorporate the Convolutional Block Attention Module(CBAM),which adaptively adjusts feature weights during the feature extraction stage to more precisely capture local anomalous information.Additionally,extensive experiments are conducted on the MVTec industrial dataset and a self-made cable anomaly dataset to comprehensively evaluate the detection performance of the proposed method.The experimental results demonstrate that the proposed method outperforms multiple state-of-the-art approaches in unsupervised anomaly detec-tion tasks.Specifically,on the cable anomaly dataset,the proposed method achieves an Image-wise AUROC(Image-wise Area Under ROC)and F1-Score of 88.1％and 80.8％,respectively,outper-forming the baseline Fastflow algorithm by 11.7％and 7.8％.关键词
异常检测/无监督检测/机器视觉/视觉大模型/注意力机制Key words
anomaly detection/unsupervised detection/machine vision/vision transformer/attention mechanism分类
信息技术与安全科学引用本文复制引用
王镇,翟轲,薛赛,白双..基于通用视觉大模型与注意力增强的无监督异常检测[J].北京交通大学学报,2025,49(3):14-22,9.基金项目
国家自然科学基金(62472024) （62472024）
中国铁路北京局集团有限公司科技研究开发计划(2024BH02)National Natural Science Foundation of China(62472024) （2024BH02）
Science and Technology Research and Development Project of China Railway Beijing Group Co.,Ltd.(2024BH02) （2024BH02）
