Page 51 - Read Online

Hu et al. J. Mater. Inf. 2025, 5, 44 Journal of
DOI: 10.20517/jmi.2025.21
Materials Informatics

Research Article Open Access

Application of self-supervised learning in steel
surface defect detection

Shiyu Hu, Xudong Ma, Yuqi Zhang, Wei Xu *

State Key Laboratory of Digital Steel, Northeastern University, Shenyang 110819, Liaoning, China.
* Correspondence to: Prof. Wei Xu, State Key Laboratory of Digital Steel, Northeastern University, NO. 3-11, Wenhua Road,
Shenyang 110819, Liaoning, China. E-mail: xuwei@ral.neu.edu.cn

How to cite this article: Hu, S.; Ma, X.; Zhang, Y.; Xu, W. Application of self-supervised learning in steel surface defect detection.
J. Mater. Inf. 2025, 5, 44. https://dx.doi.org/10.20517/jmi.2025.21
Received: 1 Apr 2025 First Decision: 10 Jun 2025 Revised: 24 Jun 2025 Accepted: 8 Jul 2025 Published: 22 Jul 2025

Academic Editor: Qian Ma Copy Editor: Pei-Yun Wang Production Editor: Pei-Yun Wang

Abstract
In scientific research, effective utilization of unlabeled data has become pivotal, as exemplified by AlphaFold2,
which won the 2024 Nobel Prize. Pioneering this paradigm shift, we develop a universal self-supervised learning
methodology for detecting surface defects in steel materials. By harnessing unlabeled data, our approach
significantly reduces the dependence for manual annotation and enhances scalability while training robust models
capable of generalizing across defect types. Using a Faster R-CNN framework, we achieved a mean average
precision (mAP) of 0.385 and a mAP at IoU = 0.5 (mAP_50) of 0.768 on the NEU-DET steel defects dataset.
These results demonstrate both the efficacy of our self-supervised strategy and its potential as a framework for
developing image detection systems with minimal labeled data requirements in surface defect identification.

Keywords: Unlabelled data, self-supervised learning, deep learning, steel materials, image detection

INTRODUCTION
In recent years, deep learning (DL) has revolutionized various fields by significantly enhancing the accuracy
and capabilities of data analysis . One prominent application is in computer vision, where DL algorithms
[1]
have become indispensable tools, driving advancements in areas ranging from image recognition to
complex pattern detection .
[2-4]

© The Author(s) 2025. Open Access This article is licensed under a Creative Commons Attribution 4.0
International License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, sharing,
adaptation, distribution and reproduction in any medium or format, for any purpose, even commercially, as
long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and
indicate if changes were made.

www.oaepublish.com/jmi