.png){kind=icon}
返回
Anomaly detection based on multi-teacher knowledge distillation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.sysarc.2023.102861.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Anomaly detection on high-dimensional data is crucial for real-world industrial applications. Recent works adopt the Knowledge Distillation (KD) technique to improve the accuracy of anomaly detection Neural Networks (NN). Most KD-based solutions only adopt a single teacher NN and have not yet fully incorporated the distinct advantages of different NN structures. To fill this gap, this paper proposes a novel Multi-teacher Knowledge Distillation approach, which effectively integrates multiple teachers with importance weights to provide guidance for the accurate anomaly detection of students. However, the importance weights are hard to get when training only with normal data. To overcome this challenge, we use an autoencoder-based reconstruction process to update teacher importance weights. In the meantime, the student model parameters are optimized by giving a set of teacher importance weights. Anomalies are then detected based on the deviations between the outputs of teacher and student, as well as the reconstruction errors through the student network. Our proposed approach is evaluated on both CIFAR10 and MVTec datasets. The results show good performance on both high-level semantic anomaly detection and low-level pixel anomaly detection.
Keyword:
Anomaly detection
Multi-teacher
Knowledge distillation
Semantic and pixel anomaly
Normal feature
期刊
IF:
4.1
论文数:
3.0K
被引数:
4.2K
机构
引用论文
First-Principles Computation of the Vibrational Entropy of Ordered and DisorderedNi3Al有序和无序振动熵的第一性原理计算 Ni3Al
PREAI
分享收藏adVAE: A self-adversarial variational autoencoder with Gaussian anomaly prior knowledge for anomaly detectionadVAE: 具有高斯异常先验知识的自对抗性变分自编码器，用于异常检测
OAAI
OAAI分享收藏Ligating properties of tertiary phosphine/arsine sulphides or selenides—VI. Addition compounds of zinc(II), cadmium(II) and mercury(II) with sulphides or selenides of triphenyl- and tri-p-tolylphosphines and 1,3-trimethylenebis (diphenylphosphine).png)
Polyhedron
PolyhedronIF0
PREAI
分享收藏Out-of-Distribution Detection for Deep Neural Networks With Isolation Forest and Local Outlier FactorIEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏Review of Design Experiments Using the Taguchi Approach: 16 Steps to Product and Process Improvement
PREAI
分享收藏Landscape Seroprevalence of Three Hemorrhagic Disease-Causing Viruses in a Wild CervidEcoHealth
EcoHealthIF0
PREAI
分享收藏
查看更多内容