VajraV1在实时目标检测中精度领先，超越所有现有YOLO模型。
VajraV1 -- The most accurate Real Time Object Detector of the YOLO family
- 融合YOLO系列设计优势，优化架构提升检测精度。
- 在COCO数据集上，各尺寸模型均显著超越YOLOv12/v13，最高达56.2% mAP。
- 适合追求高精度实时检测的工业应用与部署场景。
近年来，实时目标检测取得显著进展，YOLOv10、YOLO11、YOLOv12和YOLOv13于2024至2025年间相继发布。本技术报告提出VajraV1模型架构，通过整合已有YOLO模型的有效设计，实现实时检测器中的最先进精度，同时保持优异推理速度。在COCO验证集上，VajraV1-Nano达到44.3% mAP，优于YOLOv12-N的40.6%和YOLOv13-N的41.6%，延迟与YOLOv12-N和YOLOv11-N相当；VajraV1-Small达50.4% mAP，高于YOLOv12-S和YOLOv13-S的48.0%；VajraV1-Medium为52.7% mAP，超过YOLOv12-M的52.5%；VajraV1-Large达53.7% mAP，优于YOLOv13-L的53.4%；VajraV1-Xlarge达56.2% mAP，超越所有现有实时目标检测器。
原文摘要 · Abstract (English)
Recent years have seen significant advances in real-time object detection, with the release of YOLOv10, YOLO11, YOLOv12, and YOLOv13 between 2024 and 2025. This technical report presents the VajraV1 model architecture, which introduces architectural enhancements over existing YOLO-based detectors. VajraV1 combines effective design choices from prior YOLO models to achieve state-of-the-art accuracy among real-time object detectors while maintaining competitive inference speed. On the COCO validation set, VajraV1-Nano achieves 44.3% mAP, outperforming YOLOv12-N by 3.7% and YOLOv13-N by 2.7% at latency competitive with YOLOv12-N and YOLOv11-N. VajraV1-Small achieves 50.4% mAP, exceeding YOLOv12-S and YOLOv13-S by 2.4%. VajraV1-Medium achieves 52.7% mAP, outperforming YOLOv12-M by 0.2%. VajraV1-Large achieves 53.7% mAP, surpassing YOLOv13-L by 0.3%. VajraV1-Xlarge achieves 56.2% mAP, outperforming all existing real-time object detectors.
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。