计算机与现代化Issue(2)：58-63,85,7.DOI:10.3969/j.issn.1006-2475.2025.02.008
基于双向多尺度知识蒸馏的异常检测算法
Anomaly Detection Algorithm Based on Bidirectional Multi-scale Knowledge Distillation
刘重宜 1李华 1任德均 1柳尧凯 1王玉龙1
作者信息
- 1. 四川大学机械工程学院,四川 成都 610065
- 折叠
摘要
Abstract
Aiming at the problem of low anomaly detection and localization accuracy in current knowledge distillation-based anomaly detection algorithms due to the low difference in abnormal feature representation between teacher and student models,an anomaly detection algorithm based on bidirectional multi-scale knowledge distillation is proposed.An asymmetric teacher-student network structure composed of a teacher model,a student model and a reverse distillation student model is employed to suppress the student's generalization to abnormal features.A feature fusion residual module is introduced between the bidirec-tional distillation student models to integrate multi-scale features and reduce abnormal disturbances.An attention module is intro-duced within the forward distillation student model to enhance the learning ability of important features.During the testing phase,anomaly assessment is performed through multi-scale anomaly map fusion.Experimental results on the public dataset MVTec AD show that the proposed algorithm,using ResNet18 as the backbone,achieves high scores of 97.7%at the pixel level and 98.8%at the image level on the area under the receiver operating characteristic curve evaluation metric,effectively improving the cur-rent knowledge distillation algorithms.关键词
异常检测/知识蒸馏/特征融合/注意力/深度学习Key words
anomaly detection/knowledge distillation/feature fusion/attention/deep learning分类
计算机与自动化引用本文复制引用
刘重宜,李华,任德均,柳尧凯,王玉龙..基于双向多尺度知识蒸馏的异常检测算法[J].计算机与现代化,2025,(2):58-63,85,7.
