YOLOv11提升小物体检测精度，兼顾实时性。
YOLOv11 Demystified: A Practical Guide to High-Performance Object Detection
- 引入C3K2、SPPF和C2PSA模块增强特征提取
- mAP提升且推理速度保持实时水平
- 适合自动驾驶与视频监控等场景
YOLOv11是You Only Look Once系列最新的实时目标检测模型，通过创新的架构模块提升特征提取能力与小物体检测性能。本文详细分析了YOLOv11的主干网络、颈部和头部结构，其关键创新包括C3K2模块、空间金字塔池化-快速版（SPPF）以及跨阶段部分空间注意力（C2PSA）模块，有效增强空间特征处理能力并维持高速推理。在标准基准测试中，与前代YOLO版本相比，YOLOv11在平均精度（mAP）和推理速度上均实现显著提升。结果表明，YOLOv11在不牺牲实时性的前提下获得更高检测精度，适用于自动驾驶、安防监控和视频分析等实际应用。本研究为后续研究提供了清晰的参考框架。
原文摘要 · Abstract (English)
YOLOv11 is the latest iteration in the You Only Look Once (YOLO) series of real-time object detectors, introducing novel architectural modules to improve feature extraction and small-object detection. In this paper, we present a detailed analysis of YOLOv11, including its backbone, neck, and head components. The model key innovations, the C3K2 blocks, Spatial Pyramid Pooling - Fast (SPPF), and C2PSA (Cross Stage Partial with Spatial Attention) modules enhance spatial feature processing while preserving speed. We compare YOLOv11 performance to prior YOLO versions on standard benchmarks, highlighting improvements in mean Average Precision (mAP) and inference speed. Our results demonstrate that YOLOv11 achieves superior accuracy without sacrificing real-time capabilities, making it well-suited for applications in autonomous driving, surveillance, and video analytics.This work formalizes YOLOv11 in a research context, providing a clear reference for future studies.
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。