A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS
Instituto Politecnico Nacional（墨西哥国立理工学院）；CICATA-Qro；Universidad Autónoma de Querétaro（克雷塔罗自治大学）；Facultad de Informática（信息学院）
Juan Terven, Diana Cordova-Esparza
备注：
36 pages, 21 figures, 4 tables, published in Machine Learning and Knowledge Extraction. This version contains the last changes made to the published version
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.
Georgia Institute of Technology（佐治亚理工学院）；The Cooper Union（库珀联盟学院）；UNC Wilmington（北卡罗来纳大学威尔明顿分校）
This paper focuses on YOLO-LITE, a real-time object detection model developed to run on portable devices such as a laptop or cellphone lacking a Graphics Processing Unit (GPU). The model was first trained on the PASCAL VOC dataset then on the COCO dataset, achieving a mAP of 33.81% and 12.26% respectively. YOLO-LITE runs at about 21 FPS on a non-GPU computer and 10 FPS after implemented onto a website with only 7 layers and 482 million FLOPS. This speed is 3.8x faster than the fastest state of art model, SSD MobilenetvI. Based on the original object detection algorithm YOLOV2, YOLO- LITE was d…
YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systems
Institute of Information Science, Academia Sinica（中央研究院资讯科学研究所）；National Taipei University of Technology（台北科技大学）；National Chung Hsing University（国立中兴大学）
Mirror-Yolo: A Novel Attention Focus, Instance Segmentation and Mirror Detection Model
University of Liverpool（利物浦大学）；Xi’an Jiaotong-Liverpool University（西交利物浦大学）；JITRI Micro-Nano Automation Institute（JITRI微纳米自动化研究院）；Yunnan Normal University（云南师范大学）
Intra-YOLO: A Small Object Detection Model for Caries and Molar-Incisor Hypomineralization in Intraoral Photography Based on Transfer Learning with Reinforcement Learning
Department of Mechanical Engineering, College of Engineering, National Yang Ming Chiao Tung University（国家阳明交通大学机械工程系）；Taipei Medical University Hospital（台北医学大学医院）；Wan Fang Hospital, Taipei Medical University（台北医学大学万芳医院）
Object detection is one of the most important areas in computer vision, which plays a key role in various practical scenarios. Due to limitation of hardware, it is often necessary to sacrifice accuracy to ensure the infer speed of the detector in practice. Therefore, the balance between effectiveness and efficiency of object detector must be considered. The goal of this paper is to implement an object detector with relatively balanced effectiveness and efficiency that can be directly applied in actual application scenarios, rather than propose a novel detection model. Considering that YOLOv3 h…
In this work, we present and evaluate a method to perform real-time multiple drone detection and three-dimensional localization using state-of-the-art tiny-YOLOv4 object detection algorithm and stereo triangulation. Our computer vision approach eliminates the need for computationally expensive stereo matching algorithms, thereby significantly reducing the memory footprint and making it deployable on embedded systems. Our drone detection system is highly modular (with support for various detection algorithms) and capable of identifying multiple drones in a system, with real-time detection accur…
The Hong Kong University of Science and Technology（香港科技大学）；Chinese Academy of Sciences（中国科学院）
Object detection in 3D with stereo cameras is an important problem in computer vision, and is particularly crucial in low-cost autonomous mobile robots without LiDARs. Nowadays, most of the best-performing frameworks for stereo 3D object detection are based on dense depth reconstruction from disparity estimation, making them extremely computationally expensive. To enable real-world deployments of vision detection with binocular images, we take a step back to gain insights from 2D image-based detection frameworks and enhance them with stereo features. We incorporate knowledge and the inference …
ZS Associates India Private Limited（ZS咨询印度私人有限公司）；Indian Institute of Science Education and Research (IISER) Pune（浦那印度科学教育与研究学院）；Findability Sciences Inc.（Findability科学公司）；Indraprastha Institute of Information Technology (IIIT Delhi)（英德拉普拉斯塔信息技术学院（德里IIIT））；Carnegie Mellon University（卡内基梅隆大学）
Object detection is a well-known problem in computer vision. Despite this, its usage and pervasiveness in the traditional Indian food dishes has been limited. Particularly, recognizing Indian food dishes present in a single photo is challenging due to three reasons: 1. Lack of annotated Indian food datasets 2. Non-distinct boundaries between the dishes 3. High intra-class variation. We solve these issues by providing a comprehensively labelled Indian food dataset- IndianFood10, which contains 10 food classes that appear frequently in a staple Indian meal and using transfer learning with YOLOv4…
LTV-YOLO: A Lightweight Thermal Object Detector for Young Pedestrians in Adverse Conditions
Automotive and Surface Transportation National Research Council Canada（交通运输国家研究院加拿大）；Department of Civil and Environmental Engineering University of Western Ontario（土木与环境工程系温哥华大学）
Comparative Analysis of Advanced AI-based Object Detection Models for Pavement Marking Quality Assessment during Daytime
PT Mitra Solusi Telematika；Ingram School of Engineering（英格拉姆工程学院）；Texas State University（德克萨斯州立大学）；Department of Civil Engineering（土木工程系）；Rowan University（罗文大学）；Department of Geography and Environmental Studies（地理与环境研究系）
This paper introduces YotoR (You Only Transform One Representation), a novel deep learning model for object detection that combines Swin Transformers and YoloR architectures. Transformers, a revolutionary technology in natural language processing, have also significantly impacted computer vision, offering the potential to enhance accuracy and computational efficiency. YotoR combines the robust Swin Transformer backbone with the YoloR neck and head. In our experiments, YotoR models TP5 and BP4 consistently outperform YoloR P6 and Swin Transformers in various evaluations, delivering improved obj…
Purdue University（普渡大学）；Loyola University Chicago（芝加哥洛约拉大学）；Argonne National Laboratory（阿贡国家实验室）；Intel Corporation（英特尔公司）；Facebook Corporation（脸书公司（Facebook））；School of Electrical and Computer Engineering（电气与计算机工程学院）；Department of Computer Science（计算机科学系）；Argonne Leadership Computing Facility（阿贡领导力计算设施）；Santa Clara（圣克拉拉）；Menlo Park（门洛帕克）；West Lafayette, IN, USA（美国印第安纳州西拉斐特）
Computer vision relies on labeled datasets for training and evaluation in detecting and recognizing objects. The popular computer vision program, YOLO ("You Only Look Once"), has been shown to accurately detect objects in many major image datasets. However, the images found in those datasets, are independent of one another and cannot be used to test YOLO's consistency at detecting the same object as its environment (e.g. ambient lighting) changes. This paper describes a novel effort to evaluate YOLO's consistency for large-scale applications. It does so by working (a) at large scale and (b) by…
Valeo Schalter und Sensoren GmbH（法雷奥开关与传感器有限公司）；Ilmenau University of Technology（伊尔默瑙工业大学）
Accurate detection of 3D objects is a fundamental problem in computer vision and has an enormous impact on autonomous cars, augmented/virtual reality and many applications in robotics. In this work we present a novel fusion of neural network based state-of-the-art 3D detector and visual semantic segmentation in the context of autonomous driving. Additionally, we introduce Scale-Rotation-Translation score (SRTs), a fast and highly parameterizable evaluation metric for comparison of object detections, which speeds up our inference time up to 20\% and halves training time. On top, we apply state-…
University of Waterloo（滑铁卢大学）；DarwinAI Corp.（DarwinAI公司）
Object detection remains an active area of research in the field of computer vision, and considerable advances and successes has been achieved in this area through the design of deep convolutional neural networks for tackling object detection. Despite these successes, one of the biggest challenges to widespread deployment of such object detection networks on edge and mobile scenarios is the high computational and memory requirements. As such, there has been growing research interest in the design of efficient deep neural network architectures catered for edge and mobile usage. In this study, w…
Pediatric Wrist Fracture Detection Using Feature Context Excitation Modules in X-ray Images
Graduate Institute of Networking and Multimedia（网络与多媒体研究生院）；National Taiwan University（台湾大学）；Department of Electrical and Computer Engineering（电子工程系）；Tamkang University（Tamkang大学）；College of Energy and Mechanical Engineering（能源与机械工程学院）；Shanghai University of Electric Power（上海电力大学）
Recognizing Handwritten Mathematical Expressions of Vertical Addition and Subtraction
Universidade Federal Rural de Pernambuco (UFRPE)（伯南布哥联邦农村大学（UFRPE））；Universidade Federal de Pernambuco (UFPE)（伯南布哥联邦大学（UFPE））；Federal University of Alagoas（阿拉戈斯联邦大学）
YOLO with Kolmogorov-Arnold networks and vision-language foundation models for interpretable object detection with trustworthy multimodal AI in computer vision perception
University of Bath（巴斯大学）；Zhejiang University（浙江大学）
Object detection is considered one of the most challenging problems in this field of computer vision, as it involves the combination of object classification and object localization within a scene. Recently, deep neural networks (DNNs) have been demonstrated to achieve superior object detection performance compared to other approaches, with YOLOv2 (an improved You Only Look Once model) being one of the state-of-the-art in DNN-based object detection methods in terms of both speed and accuracy. Although YOLOv2 can achieve real-time performance on a powerful GPU, it still remains very challenging…
