YOLO26优化架构与部署能力，实现实时检测在边缘设备的高效运行。
YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection
- 移除DFL损失，采用无NMS端到端推理，提升推理效率。
- 在Jetson Nano上实现30帧/秒，比YOLOv8快1.8倍，支持多任务检测。
- 适合机器人、工业质检等边缘部署场景，支持多种格式量化导出。
本研究全面分析了最新发布的Ultralytics YOLO26（又称YOLOv26），聚焦其在实时目标检测中的关键架构改进与性能基准测试。该模型于2025年9月发布，专为边缘和低功耗设备设计，兼顾效率、精度与部署就绪性。论文系统阐述其创新：移除分布焦点损失（DFL），采用端到端无NMS推理，集成ProgLoss与小目标感知标签分配（STAL），并引入MuSGD优化器以实现稳定收敛。此外，YOLO26被构建为多任务框架，支持目标检测、实例分割、姿态估计、定向检测与分类。在NVIDIA Jetson Nano与Orin等边缘设备上，其性能对比了YOLOv8、YOLOv11、YOLOv12、YOLOv13及基于Transformer的检测器（RF-DETR与RT-DETR）。研究还探讨了实时部署路径、灵活导出选项（ONNX、TensorRT、CoreML、TFLite）及INT8/FP16量化策略。实际应用案例涵盖机器人、制造与物联网领域，展示跨行业适应性。最后讨论部署效率与未来发展方向。
原文摘要 · Abstract (English)
This study presents a comprehensive analysis of Ultralytics YOLO26(also called as YOLOv26), highlighting its key architectural enhancements and performance benchmarking for real-time object detection. YOLO26, released in September 2025, stands as the newest and most advanced member of the YOLO family, purpose-built to deliver efficiency, accuracy, and deployment readiness on edge and low-power devices. The paper sequentially details architectural innovations of YOLO26, including the removal of Distribution Focal Loss (DFL), adoption of end-to-end NMS-free inference, integration of ProgLoss and Small-Target-Aware Label Assignment (STAL), and the introduction of the MuSGD optimizer for stable convergence. Beyond architecture, the study positions YOLO26 as a multi-task framework, supporting object detection, instance segmentation, pose/keypoints estimation, oriented detection, and classification. We present performance benchmarks of YOLO26 on edge devices such as NVIDIA Jetson Nano and Orin, comparing its results with YOLOv8, YOLOv11, YOLOv12, YOLOv13, and transformer-based detectors(RF-DETR and RT-DETR). This paper further explores real-time deployment pathways, flexible export options (ONNX, TensorRT, CoreML, TFLite), and quantization for INT8/FP16. Practical use cases of YOLO26 across robotics, manufacturing, and IoT are highlighted to demonstrate cross-industry adaptability. Finally, insights on deployment efficiency and broader implications are discussed, with future directions for YOLO26 and the YOLO lineage outlined.
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。