Insulator Surface Defect Detection Method Based on Graph Feature Diffusion Distillation

Shucai Li

doi:10.3390/jimaging11060190

Insulator Surface Defect Detection Method Based on Graph Feature Diffusion Distillation

2025-08-04

0

OA

AI

DOI：10.3390/jimaging11060190

Original

Original request for help

Save

Abstract

En 中文

Aiming at the difficulties of scarcity of defect samples on the surface of power insulators, irregular morphology and insufficient pixel-level localization accuracy, this paper proposes a defect detection method based on graph feature diffusion distillation named GFDD. The feature bias problem is alleviated by constructing a dual-division teachers architecture with graph feature consistency constraints, while the cross-layer feature fusion module is utilized to dynamically aggregate multi-scale information to reduce redundancy; the diffusion distillation mechanism is designed to break through the traditional single-layer feature transfer limitation, and the global context modeling capability is enhanced by fusing deep semantics and shallow details through channel attention. In the self-built dataset, GFDD achieves 96.6% Pi.AUROC, 97.7% Im.AUROC and 95.1% F1-score, which is 2.4–3.2% higher than the existing optimal methods; it maintains excellent generalization and robustness in multiple public dataset tests. The method provides a high-precision solution for automated inspection of insulator surface defect and has certain engineering value.

Keywords:

defect detection

graph feature diffusion distillation

power insulator

pixel-level localization

cross-layer feature fusion

Insulator Surface Defect Detection Method Based on Graph Feature Diffusion Distillation

Abstract

Journal

Organization