YOLOv6通过新架构实现高精度实时目标检测
What is YOLOv6? A Deep Insight into the Object Detection Model
- 采用EfficientRep骨干和Rep-PAN颈部，提升特征提取与融合能力
- YOLOv6-N达37.5% AP、1187 FPS，YOLOv6-S达45.0% AP、484 FPS
- 适合需要高精度与实时性的工业视觉场景
本文深入分析YOLOv6目标检测模型的设计框架、优化技术及检测性能。其核心由EfficientRep骨干网络负责鲁棒特征提取，Rep-PAN颈部实现高效特征聚合，保障高性能检测。在COCO数据集上，YOLOv6-N在NVIDIA Tesla T4 GPU上达到37.5% AP、1187 FPS；YOLOv6-S实现45.0% AP、484 FPS，优于同级别模型如PPYOLOE-S、YOLOv5-S、YOLOX-S和YOLOv8-S。YOLOv6-M与YOLOv6-L分别取得50.0%与52.8%的精度，推理速度与同类检测器相当。通过升级骨干与颈部结构，YOLOv6-L6实现实时场景下的顶尖检测精度。
原文摘要 · Abstract (English)
This work explores the YOLOv6 object detection model in depth, concentrating on its design framework, optimization techniques, and detection capabilities. YOLOv6's core elements consist of the EfficientRep Backbone for robust feature extraction and the Rep-PAN Neck for seamless feature aggregation, ensuring high-performance object detection. Evaluated on the COCO dataset, YOLOv6-N achieves 37.5\% AP at 1187 FPS on an NVIDIA Tesla T4 GPU. YOLOv6-S reaches 45.0\% AP at 484 FPS, outperforming models like PPYOLOE-S, YOLOv5-S, YOLOX-S, and YOLOv8-S in the same class. Moreover, YOLOv6-M and YOLOv6-L also show better accuracy (50.0\% and 52.8\%) while maintaining comparable inference speeds to other detectors. With an upgraded backbone and neck structure, YOLOv6-L6 delivers cutting-edge accuracy in real-time.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。