Implicit multi-teacher distillation for unsupervised industrial anomaly detection

Lanlan WU; Gaoming YANG; Xiujun WANG; Ji ZHANG; Zhi LIU

doi:10.1631/ENG.ITEE.2026.0151

Your Location：

Home >

Browse articles >

Implicit multi-teacher distillation for unsupervised industrial anomaly detection

Regular Papers | Updated：2026-11-05

- Implicit multi-teacher distillation for unsupervised industrial anomaly detection
- Implicit multi-teacher distillation for unsupervised industrial anomaly detection
- ENGINEERING Information Technology & Electronic Engineering Vol. 27, Issue 10, Pages: 1-10(2026)
- Affiliations：
  
  State Key Laboratory of Digital Intelligent Technology for Unmanned Coal Mining, Anhui University of Science and Technology, Huainan 232001, China
  School of Computer Science and Engineering, Anhui University of Science and Technology, Huainan 232001, China
  The First Hospital of Anhui University of Science and Technology, Huainan 232001, China
  School of Computer Science and Technology, Anhui University of Technology, Ma'anshan 243032, China
  School of Mathematics, Physics and Computing, University of Southern Queensland, Toowoomba 4350, Australia
  Department of Computer and Network Engineering, The University of Electro-Communications, Tokyo 182-8585, Japan
- Author bio：
  
  ✉ Gaoming YANG, gmyang@aust.edu.cn
  ✉ Ji ZHANG, Ji.Zhang@usq.edu.au
- Funds：
- DOI：10.1631/ENG.ITEE.2026.0151
  CLC： TP391
- Received：20 May 2026，
  
  Revised：2026-09-09，
  
  Published：01 October 2026
- Accepted：
Scan QR Code
Lanlan WU, Gaoming YANG, Xiujun WANG, et al. Implicit multi-teacher distillation for unsupervised industrial anomaly detection[J]. ENGINEERING Information Technology & Electronic Engineering, 2026, 27(10): 1-10.
DOI：

Lanlan WU, Gaoming YANG, Xiujun WANG, et al. Implicit multi-teacher distillation for unsupervised industrial anomaly detection[J]. ENGINEERING Information Technology & Electronic Engineering, 2026, 27(10): 1-10. DOI： 10.1631/ENG.ITEE.2026.0151.

摘要

Abstract

Industrial anomaly detection is important for intelligent manufacturing since defects can degrade product reliability. Existing methods based on knowledge distillation typically use a single teacher

limiting feature diversity and robustness. Multi-teacher methods often require explicit feature alignment across different network architectures

which may introduce semantic conflicts and weaken anomaly responses. We propose implicit multi-teacher distillation (IMTD) for industrial anomaly detection. IMTD employs three complementary teacher networks

namely ResNet18

ResNet34

and Wide-ResNet50

to capture texture

structural

and semantic representations from different feature spaces. Each teacher is paired with an independent decoder trained only on normal samples

enabling implicit knowledge transfer without cross-architecture feature alignment. A false-negative-aware maximum response aggregation (FN-MRA) module is further introduced to preserve the strongest anomaly evidence during fusion. Experiments on MVTec anomaly detection (MVTec AD)

visual anomaly benchmark (VisA)

and metal part defect dataset (MPDD) show that IMTD consistently outperforms recent state-of-the-art methods in both image-level and pixel-level anomaly detection. The results demonstrate the effectiveness of combining complementary teachers

implicit reconstruction

and maximum-response aggregation under anomaly-scarce conditions.

关键词

Keywords

references

Ahmad M , Rehman A , 2025 . Multi-source information fusion for anomaly detection in smart grids using federated learning . Chin J Inform Fus , 2 ( 2 ): 157 - 170 . https://doi.org/10.62762/CJIF.2025.220738 https://doi.org/10.62762/CJIF.2025.220738

Batzner K , Heckler L , König R , 2024 . EfficientAD: accurate visual anomaly detection at millisecond-level latencies . Proc IEEE/CVF Winter Conf on Applications of Computer Vision , p. 127 - 137 . https://doi.org/10.1109/WACV57701.2024.00020 https://doi.org/10.1109/WACV57701.2024.00020

Bergmann P , Fauser M , Sattlegger D , et al. , 2019 . MVTec AD—a comprehensive real-world dataset for unsupervised anomaly detection . Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition , p. 9584 - 9592 . https://doi.org/10.1109/CVPR.2019.00982 https://doi.org/10.1109/CVPR.2019.00982

Cai YX , Liang DK , Luo DL , et al. , 2024 . A discrepancy aware framework for robust anomaly detection . IEEE Trans Ind Inform , 20 ( 3 ): 3986 - 3995 . https://doi.org/10.1109/TII.2023.3318302 https://doi.org/10.1109/TII.2023.3318302

Cao YK , Zhang JN , Frittoli L , et al. , 2024 . AdaCLIP: adapting CLIP with hybrid learnable prompts for zero-shot anomaly detection . Proc 18 th European Conf on Computer Vision , p. 55 - 72 . https://doi.org/10.1007/978-3-031-72761-0_4 https://doi.org/10.1007/978-3-031-72761-0_4

Chen QY , Luo HY , Lv CK , et al. , 2025 . A unified anomaly synthesis strategy with gradient ascent for industrial anomaly detection and localization . Proc European Conf on Computer Vision , p. 37 - 54 . https://doi.org/10.1007/978-3-031-72855-6_3 https://doi.org/10.1007/978-3-031-72855-6_3

Cheng H , Luo JX , Zhang XY , 2025 . Multimodal industrial anomaly detection via UNI-modal and cross-modal fusion . IEEE Trans Ind Inform , 21 ( 6 ): 5000 - 5010 . https://doi.org/10.1109/TII.2025.3552723 https://doi.org/10.1109/TII.2025.3552723

Deng HQ , Li XY , 2022 . Anomaly detection via reverse distillation from one-class embedding . Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition , p. 9727 - 9736 . https://doi.org/10.1109/CVPR52688.2022.00951 https://doi.org/10.1109/CVPR52688.2022.00951

Gu ZH , Zhang JN , Liu L , et al. , 2024 . Rethinking reverse distillation for multi-modal anomaly detection . Proc 38 th AAAI Conf on Artificial Intelligence , 38 ( 8 ): 8445 - 8453 . https://doi.org/10.1609/AAAI.v38i8.28687 https://doi.org/10.1609/AAAI.v38i8.28687

Hendria WF , Kim H , Seo D , 2025 . Multi-model anomaly detection for industrial inspection with dynamic loss weighting and soft-hard features loss . Neur Comput Appl , 37 ( 21 ): 17031 - 17054 . https://doi.org/10.1007/s00521-025-11367-3 https://doi.org/10.1007/s00521-025-11367-3

Jeong J , Zou Y , Kim T , et al. , 2023 . WinCLIP: zero-/few-shot anomaly classification and segmentation . Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition , p. 19606 - 19616 . https://doi.org/10.1109/CVPR52729.2023.01878 https://doi.org/10.1109/CVPR52729.2023.01878

Jezek S , Jonak M , Burget R , et al. , 2021 . Deep learning-based defect detection of metal parts: evaluating current methods in complex conditions . Proc 13 th Int Congress on Ultra Modern Telecommunications and Control Systems and Workshops , p. 66 - 71 . https://doi.org/10.1109/ICUMT54235.2021.9631567 https://doi.org/10.1109/ICUMT54235.2021.9631567

Li N , Liu AJ , Zhu ZW , et al. , 2025 . Knowledge distillation-based anomaly detection via adaptive discrepancy optimization . IEEE Trans Ind Inform , 21 ( 9 ): 7176 - 7187 . https://doi.org/10.1109/TII.2025.3574540 https://doi.org/10.1109/TII.2025.3574540

Li XR , Huang ZM , Xue F , et al. , 2024 . MuSc: zero-shot industrial anomaly classification and segmentation with mutual scoring of the unlabeled images . Proc Int Conf on Learning Representations .

Liu Y , Zhang CS , Dong XJ , et al. , 2025 . A multimodal industrial anomaly detection method based on mask training and teacher–student joint memory . Eng Appl Artif Intell , 161 : 112299 . https://doi.org/10.1016/j.engappai.2025.112299 https://doi.org/10.1016/j.engappai.2025.112299

Luo JZ , Cai Y , Cai J , et al. , 2025 . STMBAD: spatio-temporal multimodal behavior anomaly detector for industrial control systems . IEEE Trans Ind Inform , 21 ( 5 ): 3746 - 3755 . https://doi.org/10.1109/TII.2025.3528559 https://doi.org/10.1109/TII.2025.3528559

Luo W , Yao HM , Yu WY , et al. , 2025 . AMI-Net: adaptive mask inpainting network for industrial anomaly detection and localization . IEEE Trans Autom Sci Eng , 22 : 1591 - 1605 . https://doi.org/10.1109/TASE.2024.3368142 https://doi.org/10.1109/TASE.2024.3368142

Ma Y , Jiang X , Guan N , et al. , 2023 . Anomaly detection based on multi-teacher knowledge distillation . J Syst Archit , 138 : 102861 . https://doi.org/10.1016/j.sysarc.2023.102861 https://doi.org/10.1016/j.sysarc.2023.102861

Ma ZQ , Li JX , Wong WK , 2025 . Patch distance based auto-encoder for industrial anomaly detection . Expert Syst Appl , 270 : 126537 . https://doi.org/10.1016/j.eswa.2025.126537 https://doi.org/10.1016/j.eswa.2025.126537

Sun H , Cao YK , Dong H , et al. , 2025 . Unseen visual anomaly generation . Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition , p. 25508 - 25517 . https://doi.org/10.1109/CVPR52734.2025.02375 https://doi.org/10.1109/CVPR52734.2025.02375

Tien TD , Nguyen AT , Tran NH , et al. , 2023 . Revisiting reverse distillation for anomaly detection . Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition , p. 24511 - 24520 . https://doi.org/10.1109/CVPR52729.2023.02348 https://doi.org/10.1109/CVPR52729.2023.02348

Wahid JA , Ayoub M , Xu ML , et al. , 2025 . NN2ViT: neural networks and vision transformers based approach for visual anomaly detection in industrial images . Neurocomputing , 615 : 128845 . https://doi.org/10.1016/j.neucom.2024.128845 https://doi.org/10.1016/j.neucom.2024.128845

Wang RX , Li Z , Zheng L , et al. , 2025 . Deep feature clustering for multi-class industrial image anomaly detection . Knowl-Based Syst , 311 : 113134 . https://doi.org/10.1016/j.knosys.2025.113134 https://doi.org/10.1016/j.knosys.2025.113134

Wei CY , Han H , Xia Y , et al. , 2025 . TDAD: self-supervised industrial anomaly detection with a two-stage diffusion model . Comput Ind , 164 : 104192 . https://doi.org/10.1016/j.compind.2024.104192 https://doi.org/10.1016/j.compind.2024.104192

Xu MH , Zhu CP , Feng G , et al. , 2025 . Multitask hybrid knowledge distillation for unsupervised anomaly detection . IEEE Trans Ind Inform , 21 ( 7 ): 5666 - 5676 . https://doi.org/10.1109/TII.2025.3556083 https://doi.org/10.1109/TII.2025.3556083

Xu MH , Qu LL , Nie ZH , et al. , 2026 . Towards reliable medical unsupervised anomaly detection: a benchmark and dataset for PET/CT with cross-modality knowledge distillation network . Inform Fus , 133 : 104341 . https://doi.org/10.1016/j.inffus.2026.104341 https://doi.org/10.1016/j.inffus.2026.104341

Zhang H , Wang Z , Zeng D , et al. , 2025 . DiffusionAD: norm-guided one-step denoising diffusion for anomaly detection . IEEE Trans Patt Anal Mach Intell , 47 ( 8 ): 7140 - 7152 . https://doi.org/10.1109/TPAMI.2025.3570494 https://doi.org/10.1109/TPAMI.2025.3570494

Zhang HL , Chen DF , Wang C , 2023 . Adaptive multi-teacher knowledge distillation with meta-learning . Proc IEEE Int Conf on Multimedia and Expo , p. 1943 - 1948 . https://doi.org/10.1109/ICME55011.2023.00333 https://doi.org/10.1109/ICME55011.2023.00333

Zhang X , Li SY , Li X , et al. , 2023 . DeSTSeg: segmentation guided denoising student-teacher for anomaly detection . Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition , p. 3914 - 3923 . https://doi.org/10.1109/CVPR52729.2023.00381 https://doi.org/10.1109/CVPR52729.2023.00381

Zhang ZL , Zhao ZB , Zhang XW , et al. , 2023 . Industrial anomaly detection with domain shift: a real-world dataset and masked multi-scale reconstruction . Comput Ind , 151 : 103990 . https://doi.org/10.1016/j.compind.2023.103990 https://doi.org/10.1016/j.compind.2023.103990

Zhong YZ , Guo B , Sun ZM , et al. , 2026 . MSDCIR-AD: unsupervised anomaly detection via multi-criteria semantic distances and constrained image reconstruction . Comput Ind , 178 : 104467 . https://doi.org/10.1016/j.compind.2026.104467 https://doi.org/10.1016/j.compind.2026.104467

Zou Y , Jeong J , Pemula L , et al. , 2022 . Spot-the-difference self-supervised pre-training for anomaly detection and segmentation . Proc 17 th European Conf on Computer Vision , p. 392 - 408 . https://doi.org/10.1007/978-3-031-20056-4_23 https://doi.org/10.1007/978-3-031-20056-4_23

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

SigmaGait: silhouette-guided motion-augmentation module for depth-based gait recognition

Social radar Doppler: multi-scenario validation ofsocial media-based crisis early warning

Relation-aware place recognition network for large-scale point clouds

Dynamic trend perception for fine-grained unmanned aerial vehicle anomaly detection in flight data

Adaptive practical fixed-time tracking control with prescribed performance for robotic manipulators

Related Author

Baojin Wang

Renhao Hu

Jinguo Li

Hongjiao Li

Zhaohui Wang

Chun Chen

Yan Feng

Deshi Ye

Related Institution

College of Computer Science and Technology, Shanghai University of Electric Power

College of Computer Science and Technology, Zhejiang University

Department of Computer Science, Zhejiang University

School of Software Technology, Zhejiang University

School of Public Affairs, Zhejiang University

Chat

Address：Zhejiang University Press, 148 Tianmushan Road, Hangzhou, China Postal code：310028
Tel：+86-571-88273162 Email：fitee@zju.edu.cn
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰