An enhanced YOLOv11 model developed for printed circuit board inspection achieved mean average precision of 96.1% at an intersection-over-union threshold of 0.5 and 56.0% across thresholds from 0.5 to 0.95 on a PCB defect dataset. The study, published in Scientific Reports by Anlong Yuan and Jingmin Li, addresses two persistent problems in PCB defect detection: a high miss rate for tiny defects and frequent false positives associated with complex background textures. The authors built CDA-YOLO around three proposed modifications designed to retain fine details, capture information at different scales and emphasize defect-related regions while suppressing background noise.

The first modification is a Cross-level Bidirectional Feature Pyramid Network, or CBiFPN. According to the paper, this component is designed to reduce the loss of fine-grained information about small targets as features pass through deep layers. The second is a lightweight DualScaleConv module, which uses parallel branches to capture local details and global contextual information.

The third component is a parameter-free average attention mechanism, abbreviated PfAAM, integrated into the C3k2 module. Its stated purpose is to strengthen the feature response in regions associated with defects and suppress background noise. These architectural changes were evaluated as a single model against the baseline YOLOv11 on the PCB defect dataset.

The reported [email protected] of 96.1% and [email protected]:0.95 of 56.0% characterize performance on that benchmark rather than on independently documented factory deployments. The supplied article abstract does not describe separate tests across different PCB designs, imaging systems, production lines or defect categories, so the scope of the demonstrated gain is limited to the reported dataset evaluation.

Subject of Research: Experimental evaluation of an enhanced YOLOv11 model for detecting defects in printed circuit boards.

Article Title: CDA-YOLO: an improved YOLOv11 model for PCB defect detection

Article References: Yuan, A., & Li, J. (2026). CDA-YOLO: an improved YOLOv11 model for PCB defect detection. Scientific Reports. https://doi.org/10.1038/s41598-026-74471-x

Image Credits: AI Generated

DOI: 10.1038/s41598-026-74471-x

Keywords: PCB defect detection, YOLOv11, CDA-YOLO, computer vision, small-object detection, feature fusion, dual-scale convolution, attention mechanism, printed circuit boards, improved, model, defect

News Source: Denise Maddox. (October 20, 2026). CDA-YOLO improves PCB defect detection over YOLOv11. Scienmag.