Scholarlink

<p>Quality assurance in industrial manufacturing relies heavily on PCB defect detection, yet it faces challenges such as complex backgrounds, minute target sizes, and significant scale variations. To address these challenges, we propose an enhanced adaptive multi-scale object detection model built upon RT-DETR, termed EAM-DETR. Firstly, an improved Faster-ELA Block is introduced, which reduces the model’s computational overhead while simultaneously enhancing detection efficiency. Secondly, we introduce the AIFI-ASSA module, which integrates adaptive sparse self-attention (ASSA) to prioritize salient features within clutter-filled backgrounds. Finally, we develop a multi-scale collaborative feature pyramid (MCFP) that preserves fine-grained features and substantially improves detection of small targets across various scales. On the PKU-Market-PCB dataset, EAM-DETR reaches 97.1% mAP50 with a throughput of 74.9 FPS, exceeding the RT-DETR baseline by 3.0% in accuracy and 16.5% in inference speed. These results demonstrate that EAM-DETR significantly accelerates inference while maintaining high accuracy, confirming its practical value and robustness for industrial PCB defect inspection.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

EAM-DETR: enhanced adaptive multi-scale DETR for PCB defect detection

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月21日

查看全文
  • Cong Chen,
  • Shuxin Liu

摘要

Quality assurance in industrial manufacturing relies heavily on PCB defect detection, yet it faces challenges such as complex backgrounds, minute target sizes, and significant scale variations. To address these challenges, we propose an enhanced adaptive multi-scale object detection model built upon RT-DETR, termed EAM-DETR. Firstly, an improved Faster-ELA Block is introduced, which reduces the model’s computational overhead while simultaneously enhancing detection efficiency. Secondly, we introduce the AIFI-ASSA module, which integrates adaptive sparse self-attention (ASSA) to prioritize salient features within clutter-filled backgrounds. Finally, we develop a multi-scale collaborative feature pyramid (MCFP) that preserves fine-grained features and substantially improves detection of small targets across various scales. On the PKU-Market-PCB dataset, EAM-DETR reaches 97.1% mAP50 with a throughput of 74.9 FPS, exceeding the RT-DETR baseline by 3.0% in accuracy and 16.5% in inference speed. These results demonstrate that EAM-DETR significantly accelerates inference while maintaining high accuracy, confirming its practical value and robustness for industrial PCB defect inspection.