IECE - Institute of Emerging and Computer Engineers

  • Sign Up Log in
    Log in
    • zhougj@hit.edu.cn
    Academic Editor
    Author
    Contributions by role
    Author 1
    Reviewer 1
    Editor 1
    ORCID
    0000-0002-1530-9321
    Gongjian Zhou
    School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin 150001, China
    Summary
    Gongjian Zhou was born in China, in 1979. He received the B.E., M.E., and Ph.D. degrees in information and communication engineering from Harbin Institute of Technology, Harbin, China, in 2000, 2002, and 2008, respectively. From February 2009 to March 2011, he held a Postdoctoral Fellowship at the Department of Aerospace Engineering, Harbin Institute of Technology. From April 2011 to May 2012, he was a Visiting Professor with the Department of Electrical and Computer Engineering, McMaster University, Hamilton, ON, Canada. He is currently a Professor with the Department of Electronic Engineering, Harbin Institute of Technology. He is also a Longjiang Young Scholar. His research interests include estimation, tracking, detection, information fusion, and signal processing.
    Edited Journals
    Chinese Journal of Information Fusion
    IECE Contributions
    Articles
    1
    Edited
    1
    Free Access | Research Article | 30 September 2024
    Unsupervised Industrial Anomaly Detection Based on Feature Mask Generation and Reverse Distillation
    by
    Pei Qi
    ,
    Lin Chai
    ,
    Xinyu Ye
    Chinese Journal of Information Fusion | Volume 1, Issue 2: 160-174, 2024 | DOI:10.62762/CJIF.2024.734267
    Abstract
    In the realm of industrial defect detection, unsupervised anomaly detection methods draw considerable attention as a result of their exceptional accomplishments. Among these, knowledge distillation-based methods have emerged as a prominent research focus, favored for their streamlined architecture, precision, and efficiency. However, the challenge of characterizing the variability in anomaly samples hinders the accuracy of detection. To address this issue, our research presents a novel approach for anomaly detection and localization, leveraging the concept of inverse knowledge distillation as its cornerstone. We employ the encoder as the guiding teacher model and designate the decoder as the... More >
    Graphical Abstract
    Unsupervised Industrial Anomaly Detection Based on Feature Mask Generation and Reverse Distillation