VajraV1 -- The most accurate Real Time Object Detector of the YOLO family

TL;DR

VajraV1 is a new YOLO-based real-time object detector that achieves state-of-the-art accuracy on the COCO dataset while maintaining competitive inference speeds.

Contribution

The paper introduces VajraV1, a novel architecture that improves accuracy over existing YOLO models without sacrificing real-time performance.

Findings

VajraV1-Nano outperforms YOLOv12-N and YOLOv13-N in mAP.

VajraV1-Xlarge achieves 56.2% mAP, surpassing all existing real-time detectors.

VajraV1 maintains competitive inference latency across variants.

Abstract

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.