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

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.

36 pages, 21 figures, 4 tables, published in Machine Learning and Knowledge Extraction. This version contains the last changes made to the published version

References in corpus (3)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Edge YOLO: Real-Time Intelligent Object Detection System Based on Edge-Cloud Cooperation in Autonomous Vehicles
• You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection

Cited by in corpus (29)

• YOLO advances to its genesis: a decadal and comprehensive review of the You Only Look Once (YOLO) series
• Surround-View Fisheye Optics in Computer Vision and Simulation: Survey and Challenges
• On the Black-box Explainability of Object Detection Models for Safe and Trustworthy Industrial Applications
• Hybrid Reasoning Based on Large Language Models for Autonomous Car Driving
• Efficient Vision-based Vehicle Speed Estimation
• Experimental validation of UAV search and detection system in real wilderness environment
• PerfCam: Digital Twinning for Production Lines Using 3D Gaussian Splatting and Vision Models
• NuSegDG: Integration of Heterogeneous Space and Gaussian Kernel for Domain-Generalized Nuclei Segmentation
• An Analysis of Layer-Freezing Strategies for Enhanced Transfer Learning in YOLO Architectures
• CCSPNet-Joint: Efficient Joint Training Method for Traffic Sign Detection Under Extreme Conditions
• Improving Small Drone Detection Through Multi-Scale Processing and Data Augmentation
• Real-Time Detection of Electronic Components in Waste Printed Circuit Boards: A Transformer-Based Approach
• An AI-Driven Multimodal Smart Home Platform for Continuous Monitoring and Assistance in Post-Stroke Motor Impairment
• Spatiotemporal Object Detection for Improved Aerial Vehicle Detection in Traffic Monitoring
• PILAR: Personalizing Augmented Reality Interactions with LLM-based Human-Centric and Trustworthy Explanations for Daily Use Cases
• TACO: Adversarial Camouflage Optimization on Trucks to Fool Object Detectors
• Efficient License Plate Recognition via Pseudo-Labeled Supervision with Grounding DINO and YOLOv8
• Layout-Aware OCR for Black Digital Archives with Unsupervised Evaluation
• IndicDLP: A Foundational Dataset for Multi-Lingual and Multi-Domain Document Layout Parsing
• Offloading Artificial Intelligence Workloads across the Computing Continuum by means of Active Storage Systems
• Vision-Language Assistant for Emotional Reactions to Risky Driving
• Attention-Augmented YOLOv8 with Ghost Convolution for Real-Time Vehicle Detection in Intelligent Transportation Systems
• SPACE-SUIT: An Artificial Intelligence Based Chromospheric Feature Extractor and Classifier for SUIT
• CSST Slitless Spectra: Target Detection and Classification with YOLO
• Improving Token-based Object Detection with Video
• Optimizing Helmet Detection with Hybrid YOLO Pipelines: A Detailed Analysis
• vNV-Heap: An Ownership-Based Virtually Non-Volatile Heap for Embedded Systems
• A Hybrid Deterministic Framework for Named Entity Extraction in Broadcast News Video
• HitoMi-Cam: A Shape-Agnostic Person Detection Method Using the Spectral Characteristics of Clothing