YOLOv12用注意力机制实现实时检测，精度和速度双突破。
YOLOv12: Attention-Centric Real-Time Object Detectors
- 以注意力为核心重构架构，兼顾高速与高精度
- 小模型达40.6% mAP，延迟仅1.64毫秒，优于同类模型
- 适合追求高精度实时检测的工程应用
长期以来，YOLO框架的改进聚焦于基于卷积神经网络（CNN）的结构优化，尽管注意力机制在建模能力上更具优势，但其速度难以媲美CNN模型。本文提出一种以注意力为中心的YOLO框架——YOLOv12，既保持了前代CNN模型的速度，又充分发挥了注意力机制的性能优势。YOLOv12在准确率上超越所有主流实时目标检测器，同时具备竞争力的推理速度。例如，YOLOv12-N在T4 GPU上实现40.6% mAP、1.64毫秒推理延迟，相比YOLOv10-N和YOLOv11-N分别提升2.1%和1.2%的mAP，且速度相当。该优势在其他模型规模中也持续存在。此外，相较于改进的端到端实时检测器如RT-DETR和RT-DETRv2，YOLOv12-S在性能上超越RT-DETR-R18和RT-DETRv2-R18，运行速度快42%，计算量仅为36%，参数量仅45%。
原文摘要 · Abstract (English)
Enhancing the network architecture of the YOLO framework has been crucial for a long time, but has focused on CNN-based improvements despite the proven superiority of attention mechanisms in modeling capabilities. This is because attention-based models cannot match the speed of CNN-based models. This paper proposes an attention-centric YOLO framework, namely YOLOv12, that matches the speed of previous CNN-based ones while harnessing the performance benefits of attention mechanisms. YOLOv12 surpasses all popular real-time object detectors in accuracy with competitive speed. For example, YOLOv12-N achieves 40.6% mAP with an inference latency of 1.64 ms on a T4 GPU, outperforming advanced YOLOv10-N / YOLOv11-N by 2.1%/1.2% mAP with a comparable speed. This advantage extends to other model scales. YOLOv12 also surpasses end-to-end real-time detectors that improve DETR, such as RT-DETR / RT-DETRv2: YOLOv12-S beats RT-DETR-R18 / RT-DETRv2-R18 while running 42% faster, using only 36% of the computation and 45% of the parameters. More comparisons are shown in Figure 1.
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。