Scholarlink

Car logo detection is crucial for intelligent transportation systems. This paper compares attention mechanisms integrated into YOLOv8m for car logo detection, evaluating Efficient Channel Attention (ECA), SimAM, and their combination against a baseline YOLOv8m (95.2% mAP@0.5, 48.6% mAP@0.5:0.95, 79.3 GFLOPs). On a dataset of 5372 images, ECA achieves 94.5% mAP@0.5 and 50.2% mAP@0.5:0.95 with 79.1 GFLOPs, SimAM reaches 96.1% mAP@0.5 and 50.0% mAP@0.5:0.95 with 79.1 GFLOPs, and the combined approach attains 95.3% mAP@0.5 and 50.1% mAP@0.5:0.95 with 79.3 GFLOPs. All variants maintain real-time performance with inference speeds of 29.29 FPS (ECA), 28.69 FPS (SimAM), and 27.95 FPS (combined), compared to the baseline’s 28.32 FPS on an NVIDIA RTX 3050 laptop GPU. These results demonstrate that integrating lightweight attention mechanisms can substantially enhance detection performance in data-constrained scenarios while preserving real-time efficiency.

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

Efficient Car Logo Detection via YOLOv8 and Attention Mechanism Fusion

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Nhat Minh Nguyen,
  • Tu Anh Nguyen,
  • Huy Thai Hinh,
  • Quang Nhat Nguyen,
  • Thong Minh Phuc Nguyen,
  • Vinh Dinh Nguyen

摘要

Car logo detection is crucial for intelligent transportation systems. This paper compares attention mechanisms integrated into YOLOv8m for car logo detection, evaluating Efficient Channel Attention (ECA), SimAM, and their combination against a baseline YOLOv8m (95.2% mAP@0.5, 48.6% mAP@0.5:0.95, 79.3 GFLOPs). On a dataset of 5372 images, ECA achieves 94.5% mAP@0.5 and 50.2% mAP@0.5:0.95 with 79.1 GFLOPs, SimAM reaches 96.1% mAP@0.5 and 50.0% mAP@0.5:0.95 with 79.1 GFLOPs, and the combined approach attains 95.3% mAP@0.5 and 50.1% mAP@0.5:0.95 with 79.3 GFLOPs. All variants maintain real-time performance with inference speeds of 29.29 FPS (ECA), 28.69 FPS (SimAM), and 27.95 FPS (combined), compared to the baseline’s 28.32 FPS on an NVIDIA RTX 3050 laptop GPU. These results demonstrate that integrating lightweight attention mechanisms can substantially enhance detection performance in data-constrained scenarios while preserving real-time efficiency.