Unsupervised selective labeling for semi-supervised industrial defect detection

In industrial detection scenarios, achieving high accuracy typically relies on extensive labeled datasets, which are costly and time-consuming. This has motivated a shift towards semi-supervised learning (SSL), which leverages labeled and unlabeled data to improve learning efficiency and reduce anno...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of King Saud University. Computer and information sciences Jg. 36; H. 8; S. 102179
Hauptverfasser: Jian Ge, Qin Qin, Shaojing Song, Jinhua Jiang, Zhiwei Shen
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Springer 01.10.2024
Schlagworte:
Industrial defect detection
Semi-supervised learning
Unsupervised spectral clustering labeling
ISSN:1319-1578
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In industrial detection scenarios, achieving high accuracy typically relies on extensive labeled datasets, which are costly and time-consuming. This has motivated a shift towards semi-supervised learning (SSL), which leverages labeled and unlabeled data to improve learning efficiency and reduce annotation costs. This work proposes the unsupervised spectral clustering labeling (USCL) method to optimize SSL for industrial challenges like defect variability, rarity, and complex distributions. Integral to USCL, we employ the multi-task fusion self-supervised learning (MTSL) method to extract robust feature representations through multiple self-supervised tasks. Additionally, we introduce the Enhanced Spectral Clustering (ESC) method and a dynamic selecting function (DSF). ESC effectively integrates both local and global similarity matrices, improving clustering accuracy. The DSF maximally selects the most valuable instances for labeling, significantly enhancing the representativeness and diversity of the labeled data. USCL consistently improves various SSL methods compared to traditional instance selection methods. For example, it boosts Efficient Teacher by 5%, 6.6%, and 7.8% in mean Average Precision(mAP) on the Automotive Sealing Rings Defect Dataset, the Metallic Surface Defect Dataset, and the Printed Circuit Boards (PCB) Defect Dataset with 10% labeled data. Our work sets a new benchmark for SSL in industrial settings.
ISSN:1319-1578
DOI:10.1016/j.jksuci.2024.102179