Abstract
Insulator defect detection in power inspection tasks faces significant challenges due to the large variations in defect sizes and complex backgrounds, which hinder the accurate identification of both small and large defects. To overcome these issues, we propose a novel dual-branch YOLO-based algorithm (DB-YOLO), built upon the YOLOv11 architecture. The model introduces two dedicated branches, each tailored for detecting large and small defects, respectively, thereby enhancing robustness and precision across multiple scales. To further strengthen global feature representation, the Mamba mechanism is integrated, improving the detection of large defects in cluttered scenes. An adaptive weighted CIoU loss function, designed based on defect size, is employed to refine localization during training. Additionally, ShuffleNetV2 is embedded as a lightweight backbone to boost inference speed without compromising accuracy. We evaluate DB-YOLO on the following three datasets: the open source CPLID, a self-built insulator defect dataset, and GC-10. Experimental results demonstrate that DB-YOLO achieves superior performance in both accuracy and real-time efficiency compared to existing state-of-the-art methods. These findings suggest that the proposed approach offers strong potential for practical deployment in real-world power inspection applications.