A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS
Machine Learning and Knowledge Extraction · 2023-11-20 · 5 (4) · 1680-1716
DOI: 10.3390/make5040083 ↗At a glance
Journal article in Machine Learning and Knowledge Extraction, published online on 2023-11-20. Written by Juan Terven and 2 co-authors. Cited 3115 times so far (Crossref); 139 references. The full text is freely available (open access, CC BY 4.0). Funded by: Instituto Politecnico Nacional.
Abstract (original language)
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.
Funding
- Instituto Politecnico Nacional
Cite
APA
Terven, J., Córdova-Esparza, D., & Romero-González, J. (2023). A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS. Machine Learning and Knowledge Extraction, 5(4), 1680-1716. https://doi.org/10.3390/make5040083
Vancouver
Terven J, Córdova-Esparza D, Romero-González J. A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS. Machine Learning and Knowledge Extraction. 2023;5(4):1680-1716. doi:10.3390/make5040083
BibTeX
@article{Terven2023,
author = {Terven, Juan and Córdova-Esparza, Diana-Margarita and Romero-González, Julio-Alejandro},
title = {A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS},
journal = {Machine Learning and Knowledge Extraction},
year = {2023},
volume = {5},
number = {4},
pages = {1680--1716},
doi = {10.3390/make5040083}
}
EUVIMED