A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS

TL;DR

This paper provides a comprehensive review of the evolution of YOLO object detection architectures from YOLOv1 to YOLOv8, YOLO-NAS, and YOLO with Transformers, highlighting innovations, training techniques, and future directions.

Contribution

It offers an in-depth analysis of each YOLO version's architectural changes, training strategies, and key contributions, serving as a valuable resource for future research.

Findings

Detailed comparison of YOLO architectures and their improvements

Identification of key innovations in each YOLO version

Insights into future research directions for real-time detection

Abstract

YOLO has become a central real-time object detection system for robotics, driverless cars, and video monitoring applications. We present a comprehensive analysis of YOLO's evolution, examining the innovations and contributions in each iteration from the original YOLO up to YOLOv8, YOLO-NAS, and YOLO with Transformers. We start by describing the standard metrics and postprocessing; then, we discuss the major changes in network architecture and training tricks for each model. Finally, we summarize the essential lessons from YOLO's development and provide a perspective on its future, highlighting potential research directions to enhance real-time object detection systems.