Contrastive self-supervised representation learning framework for metal surface defect detection

被引:2
|
作者
Zabin, Mahe [1 ]
Kabir, Anika Nahian Binte [2 ]
Kabir, Muhammad Khubayeeb [2 ]
Choi, Ho-Jin [1 ]
Uddin, Jia [3 ]
机构
[1] Korea Adv Inst Sci & Technol, Korea Adv Inst Sci & Technol, Sch Comp, Daejeon, South Korea
[2] Brac Univ, Dept Comp Sci & Engn, Sch Data & Sci, Dhaka, Bangladesh
[3] Woosong Univ, Endicott Coll, AI & Big Data Dept, Daejeon, South Korea
关键词
Metal surface defects; Lightweight convolutional encoder; Semi-supervised learning; Self-supervised learning; ANOMALY DETECTION; VISION; LOCALIZATION; INSPECTION;
D O I
10.1186/s40537-023-00827-z
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Automated detection of defects on metal surfaces is crucial for ensuring quality control. However, the scarcity of labeled datasets for emerging target defects poses a significant obstacle. This study proposes a self-supervised representation-learning model that effectively addresses this limitation by leveraging both labeled and unlabeled data. The proposed model was developed based on a contrastive learning framework, supported by an augmentation pipeline and a lightweight convolutional encoder. The effectiveness of the proposed approach for representation learning was evaluated using an unlabeled pretraining dataset created from three benchmark datasets. Furthermore, the performance of the proposed model was validated using the NEU metal surface-defect dataset. The results revealed that the proposed method achieved a classification accuracy of 97.78%, even with fewer trainable parameters than the benchmark models. Overall, the proposed model effectively extracted meaningful representations from unlabeled image data and can be employed in downstream tasks for steel defect classification to improve quality control and reduce inspection costs.
引用
收藏
页数:24
相关论文
共 50 条
  • [41] TCGL: Temporal Contrastive Graph for Self-Supervised Video Representation Learning
    Liu, Yang
    Wang, Keze
    Liu, Lingbo
    Lan, Haoyuan
    Lin, Liang
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 31 : 1978 - 1993
  • [42] Self-Supervised Facial Motion Representation Learning via Contrastive Subclips
    Sun, Zheng
    Torrie, Shad A.
    Sumsion, Andrew W.
    Lee, Dah-Jye
    ELECTRONICS, 2023, 12 (06)
  • [43] Pose-disentangled Contrastive Learning for Self-supervised Facial Representation
    Liu, Yuanyuan
    Wang, Wenbin
    Zhan, Yibing
    Feng, Shaoze
    Liu, Kejun
    Chen, Zhe
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 9717 - 9728
  • [44] Self-Supervised Video Representation Learning with Meta-Contrastive Network
    Lin, Yuanze
    Guo, Xun
    Lu, Yan
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 8219 - 8229
  • [45] Self-supervised contrastive representation learning for classifying Internet of Things malware
    Wang, Fangwei
    Chen, Yinhe
    Gao, Hongfeng
    Li, Qingru
    Wang, Changguang
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2025, 150
  • [46] Adversarial Self-Supervised Contrastive Learning
    Kim, Minseon
    Tack, Jihoon
    Hwang, Sung Ju
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS (NEURIPS 2020), 2020, 33
  • [47] A Survey on Contrastive Self-Supervised Learning
    Jaiswal, Ashish
    Babu, Ashwin Ramesh
    Zadeh, Mohammad Zaki
    Banerjee, Debapriya
    Makedon, Fillia
    TECHNOLOGIES, 2021, 9 (01)
  • [48] Self-Supervised Learning: Generative or Contrastive
    Liu, Xiao
    Zhang, Fanjin
    Hou, Zhenyu
    Mian, Li
    Wang, Zhaoyu
    Zhang, Jing
    Tang, Jie
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (01) : 857 - 876
  • [49] Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection
    Zheng, Yu
    Jin, Ming
    Liu, Yixin
    Chi, Lianhua
    Phan, Khoa T.
    Chen, Yi-Ping Phoebe
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (12) : 12220 - 12233
  • [50] Contrastive self-supervised learning for diabetic retinopathy early detection
    Ouyang, Jihong
    Mao, Dong
    Guo, Zeqi
    Liu, Siguang
    Xu, Dong
    Wang, Wenting
    MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING, 2023, 61 (09) : 2441 - 2452