A Deformable Attention-Based Detection Transformer with Cross-Scale Feature Fusion for Industrial Coil Spring Inspection
This addresses quality inspection for industrial coil springs, representing an incremental improvement with domain-specific application.
The paper tackles automated visual inspection of locomotive coil springs by proposing MSD-DETR, which achieves 92.4% mAP@0.5 at 98 FPS, outperforming YOLOv8 by 3.1% mAP and RT-DETR by 2.8% mAP.
Automated visual inspection of locomotive coil springs presents significant challenges due to the morphological diversity of surface defects, substantial scale variations, and complex industrial backgrounds. This paper proposes MSD-DETR (Multi-Scale Deformable Detection Transformer), a novel detection framework that addresses these challenges through three key innovations: (1) a structural re-parameterization strategy that decouples training-time multi-branch topology from inference-time efficiency, enhancing feature extraction while maintaining real-time performance; (2) a deformable attention mechanism that enables content-adaptive spatial sampling, allowing dynamic focus on defect-relevant regions regardless of morphological irregularity; and (3) a cross-scale feature fusion architecture incorporating GSConv modules and VoVGSCSP blocks for effective multi-resolution information aggregation. Comprehensive experiments on a real-world locomotive coil spring dataset demonstrate that MSD-DETR achieves 92.4\% mAP@0.5 at 98 FPS, outperforming state-of-the-art detectors including YOLOv8 (+3.1\% mAP) and the baseline RT-DETR (+2.8\% mAP) while maintaining comparable inference speed, establishing a new benchmark for industrial coil spring quality inspection.