A novel dual-student reverse knowledge distillation method for magnetic tile defect detection

Abstract Magnetic tiles surface defect detection is crucial in industrial production. However, it is difficult to effectively detect and locate defective areas in magnetic tiles due to the following problems: (1) The defect texture of the magnetic tile material is highly similar to the background te...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiyan Tang, Ao Zhang, Weian Liu
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-12339-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849333271903600640
author Jiyan Tang
Ao Zhang
Weian Liu
author_facet Jiyan Tang
Ao Zhang
Weian Liu
author_sort Jiyan Tang
collection DOAJ
description Abstract Magnetic tiles surface defect detection is crucial in industrial production. However, it is difficult to effectively detect and locate defective areas in magnetic tiles due to the following problems: (1) The defect texture of the magnetic tile material is highly similar to the background texture; (2) The image contrast between the normal and defective areas of the magnetic tile is low; (3) The size and morphology of the defects of the magnetic tile vary greatly. To address the above problems, this study proposes a novel dual-student reverse knowledge distillation framework based on reverse distillation called binary struct and detail reverse distillation (BSDRD). In this framework, a pre-trained teacher network that uses a deep learning model to learn multi-scale and multi-level feature representations serves as the feature extractor. The obtained features are processed by two student networks with different responsibilities. Specifically, the struct student dynamically fuses and compresses multi-scale features. The detail student applies wavelet transform to decompose high-level features into low-frequency and high-frequency components, and this decomposition not only retains global structural information of the high-level features but also enhances the detection ability for complex textures, gradients, and irregular defects. In addition, this paper introduces a multi-dimensional feature gated fusion loss (MD-GFLoss) to improve the model’s selectivity for key features and sensitivity to abnormal areas. Experiments on the magnetic tile defect detection dataset show that the proposed BSDRD is particularly effective in handling complex textures and small defects. It outperforms existing methods in both pixel-level and sample-level anomaly detection tasks.
format Article
id doaj-art-20b65a3ad2604c0680b1579be6b4ff13
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-20b65a3ad2604c0680b1579be6b4ff132025-08-20T03:45:56ZengNature PortfolioScientific Reports2045-23222025-07-0115111710.1038/s41598-025-12339-2A novel dual-student reverse knowledge distillation method for magnetic tile defect detectionJiyan Tang0Ao Zhang1Weian Liu2School of Computer Science and Engineering, Jiangsu University of Science and TechnologySchool of Computer Science and Engineering, Jiangsu University of Science and TechnologyWuhan Product Quality Supervision & Testing InstituteAbstract Magnetic tiles surface defect detection is crucial in industrial production. However, it is difficult to effectively detect and locate defective areas in magnetic tiles due to the following problems: (1) The defect texture of the magnetic tile material is highly similar to the background texture; (2) The image contrast between the normal and defective areas of the magnetic tile is low; (3) The size and morphology of the defects of the magnetic tile vary greatly. To address the above problems, this study proposes a novel dual-student reverse knowledge distillation framework based on reverse distillation called binary struct and detail reverse distillation (BSDRD). In this framework, a pre-trained teacher network that uses a deep learning model to learn multi-scale and multi-level feature representations serves as the feature extractor. The obtained features are processed by two student networks with different responsibilities. Specifically, the struct student dynamically fuses and compresses multi-scale features. The detail student applies wavelet transform to decompose high-level features into low-frequency and high-frequency components, and this decomposition not only retains global structural information of the high-level features but also enhances the detection ability for complex textures, gradients, and irregular defects. In addition, this paper introduces a multi-dimensional feature gated fusion loss (MD-GFLoss) to improve the model’s selectivity for key features and sensitivity to abnormal areas. Experiments on the magnetic tile defect detection dataset show that the proposed BSDRD is particularly effective in handling complex textures and small defects. It outperforms existing methods in both pixel-level and sample-level anomaly detection tasks.https://doi.org/10.1038/s41598-025-12339-2Knowledge distillationMagnetic tileDual student frameworkDefect detectionUnsupervised learning
spellingShingle Jiyan Tang
Ao Zhang
Weian Liu
A novel dual-student reverse knowledge distillation method for magnetic tile defect detection
Scientific Reports
Knowledge distillation
Magnetic tile
Dual student framework
Defect detection
Unsupervised learning
title A novel dual-student reverse knowledge distillation method for magnetic tile defect detection
title_full A novel dual-student reverse knowledge distillation method for magnetic tile defect detection
title_fullStr A novel dual-student reverse knowledge distillation method for magnetic tile defect detection
title_full_unstemmed A novel dual-student reverse knowledge distillation method for magnetic tile defect detection
title_short A novel dual-student reverse knowledge distillation method for magnetic tile defect detection
title_sort novel dual student reverse knowledge distillation method for magnetic tile defect detection
topic Knowledge distillation
Magnetic tile
Dual student framework
Defect detection
Unsupervised learning
url https://doi.org/10.1038/s41598-025-12339-2
work_keys_str_mv AT jiyantang anoveldualstudentreverseknowledgedistillationmethodformagnetictiledefectdetection
AT aozhang anoveldualstudentreverseknowledgedistillationmethodformagnetictiledefectdetection
AT weianliu anoveldualstudentreverseknowledgedistillationmethodformagnetictiledefectdetection
AT jiyantang noveldualstudentreverseknowledgedistillationmethodformagnetictiledefectdetection
AT aozhang noveldualstudentreverseknowledgedistillationmethodformagnetictiledefectdetection
AT weianliu noveldualstudentreverseknowledgedistillationmethodformagnetictiledefectdetection