YOLO系列演进全解析，新模型提升精度与部署效率
Ultralytics YOLO Evolution: An Overview of YOLO26, YOLO11, YOLOv8 and YOLOv5 Object Detectors for Computer Vision and Pattern Recognition
- 从YOLOv5到YOLO26，逐代优化架构与训练策略
- YOLO26在COCO上实现83.7% mAP，推理速度超1000FPS
- 适合工业检测、机器人等实时场景的高效部署
本文系统回顾了Ultralytics YOLO系列目标检测器的演进历程，重点分析其架构演变、基准测试、部署前景与未来挑战。从最新版本YOLO26（或YOLOv26）开始，该版本引入分布焦点损失移除、原生无NMS推理、渐进式损失平衡、小目标感知标签分配及MuSGD优化器，显著提升训练稳定性。后续依次梳理YOLO11的混合任务分配与高效模块、YOLOv8的解耦检测头与无锚预测、以及YOLOv5奠定的模块化PyTorch基础。在MS COCO数据集上对YOLOv5、YOLOv8、YOLO11和YOLO26进行量化对比，涵盖精度、召回率、F1分数、平均精度（mAP）及推理速度，揭示准确率与效率间的权衡。进一步探讨导出格式、量化策略及在机器人、农业、监控和制造中的实际应用。最后指出当前局限，如密集场景处理、CNN-Transformer融合、开放词汇检测与边缘感知训练等未来方向。
原文摘要 · Abstract (English)
This paper presents a comprehensive overview of the Ultralytics YOLO(You Only Look Once) family of object detectors, focusing the architectural evolution, benchmarking, deployment perspectives, and future challenges. The review begins with the most recent release, YOLO26 (or YOLOv26), which introduces key innovations including Distribution Focal Loss (DFL) removal, native NMS-free inference, Progressive Loss Balancing (ProgLoss), Small-Target-Aware Label Assignment (STAL), and the MuSGD optimizer for stable training. The progression is then traced through YOLO11, with its hybrid task assignment and efficiency-focused modules; YOLOv8, which advanced with a decoupled detection head and anchor-free predictions; and YOLOv5, which established the modular PyTorch foundation that enabled modern YOLO development. Benchmarking on the MS COCO dataset provides a detailed quantitative comparison of YOLOv5, YOLOv8, YOLO11, and YOLO26 (YOLOv26), alongside cross-comparisons with YOLOv12, YOLOv13, RT-DETR, and DEIM(DETR with Improved Matching). Metrics including precision, recall, F1 score, mean Average Precision, and inference speed are analyzed to highlight trade-offs between accuracy and efficiency. Deployment and application perspectives are further discussed, covering export formats, quantization strategies, and real-world use in robotics, agriculture, surveillance, and manufacturing. Finally, the paper identifies challenges and future directions, including dense-scene limitations, hybrid CNN-Transformer integration, open-vocabulary detection, and edge-aware training approaches. (Object Detection, YOLOv26, YOLO)
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。