What Is YOLOv11? An Introduction

YOLOv11 is the latest advancement in the YOLO series of computer vision models, offering improved accuracy and efficiency compared to its predecessors like YOLOv5 and YOLOv8. It supports a range of tasks including object detection, segmentation, classification, keypoint detection, and oriented bounding box detection. The model architecture introduces new components such as the C3k2 block, SPPF, and C2PSA, enhancing feature extraction and processing speed. Evaluated against the Microsoft COCO benchmark, the largest model, YOLOv11x, achieves a 54.7% mAP score, while the smallest, YOLOv11n, scores 39.5%. YOLOv11 uses the YOLO PyTorch TXT annotation format for data labeling, and Roboflow is recommended for annotation and deployment, offering both hosted API and self-hosted inference solutions. The model, released in September 2024, is covered under an AGPL-3.0 license, with a commercial license available through Roboflow.