The YOLO Framework: A Comprehensive Review of Evolution, Applications, and Benchmarks in Object Detection

This paper presents a comprehensive review of the YOLO (You Only Look Once) object detection framework, covering its evolution from YOLOv1 to YOLOv11. It highlights YOLO’s transformation from a simple real-time detector to a versatile architecture suitable for diverse applications. Key advancements such as anchor boxes, residual connections, and optimized training strategies are discussed across versions. The review also addresses differences between official YOLO versions and community-led releases like YOLOv5 and YOLOv8. Architectural changes are examined in terms of accuracy, efficiency, and scalability. The paper explores domain-specific adaptations using lightweight backbones and Transformers. Overall, it serves as a valuable resource for researchers and practitioners in the field.

Recommended citation: M. L. Ali and Z. Zhang, "The YOLO Framework: A Comprehensive Review of Evolution, Applications, and Benchmarks in Object Detection", Computers 2024, 13, 336. https://doi.org/10.3390/computers13120336
Download Paper