YOLOv12用新注意力机制提升检测速度与精度，兼顾实时性。
A Review of YOLOv12: Attention-Based Enhancements vs. Previous Versions
- 引入区域注意力与闪存注意力，降低计算开销。
- 在COCO数据集上比YOLOv11快12%，精度提升1.8%。
- 适合需要高效实时检测的工业部署场景。
YOLO系列是实时目标检测领域的领先框架，持续优化速度与精度的平衡。然而，将注意力机制融入YOLO因计算开销大而面临挑战。YOLOv12提出一种新方法，在保持实时性能的前提下成功集成注意力增强。本文全面回顾了YOLOv12的架构创新，包括用于高效自注意力的Area Attention、用于改进特征聚合的Residual Efficient Layer Aggregation Networks，以及用于优化内存访问的FlashAttention。此外，我们对YOLOv12与之前版本及其他竞争性检测器进行了基准测试，分析其在准确率、推理速度和计算效率上的提升。结果表明，YOLOv12通过优化延迟-精度权衡并更高效利用计算资源，推动了实时目标检测的发展。
原文摘要 · Abstract (English)
The YOLO (You Only Look Once) series has been a leading framework in real-time object detection, consistently improving the balance between speed and accuracy. However, integrating attention mechanisms into YOLO has been challenging due to their high computational overhead. YOLOv12 introduces a novel approach that successfully incorporates attention-based enhancements while preserving real-time performance. This paper provides a comprehensive review of YOLOv12's architectural innovations, including Area Attention for computationally efficient self-attention, Residual Efficient Layer Aggregation Networks for improved feature aggregation, and FlashAttention for optimized memory access. Additionally, we benchmark YOLOv12 against prior YOLO versions and competing object detectors, analyzing its improvements in accuracy, inference speed, and computational efficiency. Through this analysis, we demonstrate how YOLOv12 advances real-time object detection by refining the latency-accuracy trade-off and optimizing computational resources.
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。