EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Crossed Wavelet Convolution Network for Few-Shot Defect Detection of Industrial Chips

Zonghai Sun, Yiyu Lin iD, Yan Li, Zihan Lin

Sensors · 13.07.2025 · 25 (14) · 4377

DOI: 10.3390/s25144377 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 13.07.2025. Verfasst von Zonghai Sun und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Automation Science and Engineering, South China University of Technology, Guangzhou 510641, China. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National Natural Science Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In resistive polymer humidity sensors, the quality of the resistor chips directly affects the performance. Detecting chip defects remains challenging due to the scarcity of defective samples, which limits traditional supervised-learning methods requiring abundant labeled data. While few-shot learning (FSL) shows promise for industrial defect detection, existing approaches struggle with mixed-scene conditions (e.g., daytime and night-version scenes). In this work, we propose a crossed wavelet convolution network (CWCN), including a dual-pipeline crossed wavelet convolution training framework (DPCWC) and a loss value calculation module named ProSL. Our method innovatively applies wavelet transform convolution and prototype learning to industrial defect detection, which effectively fuses feature information from multiple scenarios and improves the detection performance. Experiments across various few-shot tasks on chip datasets illustrate the better detection quality of CWCN, with an improvement in mAP ranging from 2.76% to 16.43% over other FSL methods. In addition, experiments on an open-source dataset NEU-DET further validate our proposed method.

Schlagwörter

Stichwörter der Autor:innen

defect detectionfew-shot learningprototype learningwavelet transform convolution

Autor:innen und Institutionen

  • School of Automation Science and Engineering, South China University of Technology, Guangzhou 510641, China.
  • School of Automation, Nanjing University of Science and Technology, Nanjing 210094, China.

ORCID-Profile: Yiyu Lin

Förderung

  • National Natural Science Foundation of China
  • National Natural Science Project

Zitieren

APA

Sun, Z., Lin, Y., Li, Y., & Lin, Z. (2025). Crossed Wavelet Convolution Network for Few-Shot Defect Detection of Industrial Chips. Sensors, 25(14), 4377. https://doi.org/10.3390/s25144377

Vancouver

Sun Z, Lin Y, Li Y, Lin Z. Crossed Wavelet Convolution Network for Few-Shot Defect Detection of Industrial Chips. Sensors. 2025;25(14):4377. doi:10.3390/s25144377

BibTeX
@article{Sun2025,
  author = {Sun, Zonghai and Lin, Yiyu and Li, Yan and Lin, Zihan},
  title = {Crossed Wavelet Convolution Network for Few-Shot Defect Detection of Industrial Chips},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {14},
  pages = {4377},
  doi = {10.3390/s25144377}
}
Kostenlos starten →