多尺度特征融合的知识蒸馏异常检测方法

Knowledge Distillation Anomaly Detection with Multi-Scale Feature Fusion

为提高一分类异常检测方法的泛化性,提出了多尺度特征融合的知识蒸馏异常检测方法.在训练阶段,使用训练好的教师网络教授学生网络学习正常样本特征信息;在测试阶段,由于教师网络强大的泛化能力,对未见过的异常样本也有较好的表示能力,而学生网络未见过异常样本,因此,两者对异常样本的表征会产生较大差异,从而实现异常检测.为了进一步提高检测精度,采用中层特征金字塔实现多尺度特征融合,以增强对不同大小异常点的检测能力;同时,为了增大学生和教师网络对异常样本的表征差异,设计了特征重构模块对中层特征进行重构.在公开数据集MVTecAD上的实验结果表明,文中方法分别达到较高的97.8%AUC像素级得分、97.7%AUC图像级得分.

To enhance the generalization of anomaly detection,this paper proposes a multi-scale detection method based on knowledge distillation.During training,the well-pretrained teacher network is used to teach the student network to learn the feature of normal samples.During testing,the teacher network can still represent anomaly well due to its strong generalization,while the student network cannot.The difference between them makes the detection task available.Furthermore,a mid-level feature pyramid structure is adopted to enhance the ability for handling the anomaly with different size,and a feature reconstruction modular is also employed to enlarge the difference between teacher and student network for an anomaly.The method achieves 97.8%and 97.7%AUC score on pixel and image level respectively,evaluated on the public benchmark-MVTecAD.