Researchers Propose Minor Modifications to YOLOv11n for Laser-Cut Diamond Defect Detection

Researchers have published a study detailing FAS-YOLO, a lightweight defect detection model for laser-cut diamonds based on the YOLOv11n framework. The paper, titled 'Research on a lightweight model for laser-cut diamond defect detection based on multi-module collaborative optimization,' was published on 09 May 2026. 1038/s41598-026-51745-y.

Diamond is prone to defects such as cracks and ablation during laser cutting due to complex physical interactions. Traditional deep learning object detection algorithms generally face challenges like large parameter magnitudes and heavy computational burdens, making them difficult to apply in potential scenarios of resource-restricted equipment such as handheld inspection devices.

In response, the authors developed FAS-YOLO to address these limitations.

The FDConv (Frequency Domain Convolution) module is integrated to reconstruct the C3k2 feature extraction component, enhancing the capture of core defect features. The ADown (Adaptive Downsampling) module is employed to refine the downsampling layer, resolving parameter redundancy. The SEAM attention mechanism is integrated to enhance the detection head module.

The SEAM attention mechanism learns the importance of different channels and fuses channel information. It aims to focus more precisely on defect region features while suppressing background interference such as metal reflections. com reported that these modifications allow the model to maintain competitive performance with a smaller footprint.

6%. 4%. 6%.