The YOLO series has become the most popular framework for real-time object detection due to its reasonable trade-off between speed and accuracy. However, we observe that the speed and accuracy of YOLOs are negatively affected by the NMS. Recently, end-to-end Transformer-based detectors (DETRs) have provided an alternative to eliminating NMS. Nevertheless, the high computational cost limits their practicality and hinders them from fully exploiting the advantage of excluding NMS. In this paper, we propose the Real-Time DEtection TRansformer (RT-DETR), the first real-time end-to-end object detector to our best knowledge that addresses the above dilemma. We build RT-DETR in two steps, drawing on the advanced DETR: first we focus on maintaining accuracy while improving speed, followed by maintaining speed while improving accuracy. Specifically, we design an efficient hybrid encoder to expeditiously process multi-scale features by decoupling intra-scale interaction and cross-scale fusion to improve speed. Then, we propose the uncertainty-minimal query selection to provide high-quality initial queries to the decoder, thereby improving accuracy. In addition, RT-DETR supports flexible speed tuning by adjusting the number of decoder layers to adapt to various scenarios without retraining. Our RT-DETR-R50 / R101 achieves 53.1% / 54.3% AP on COCO and 108 / 74 FPS on T4 GPU, outperforming previously advanced YOLOs in both speed and accuracy. We also develop scaled RT-DETRs that outperform the lighter YOLO detectors (S and M models). Furthermore, RT-DETR-R50 outperforms DINO-R50 by 2.2% AP in accuracy and about 21 times in FPS. After pre-training with Objects365, RT-DETR-R50 / R101 achieves 55.3% / 56.2% AP. The project page: https://zhao-yian.github.io/RTDETR.
RF-DETR Object Detection vs YOLOv12 : A Study of Transformer-based and CNN-based Architectures for Single-Class and Multi-Class Greenfruit Detection in Complex Orchard Environments Under Label Ambiguity
Cornell University（康奈尔大学）；Kansas State University（堪萨斯州立大学）
LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection
Baidu Inc.（百度公司）；The University of Adelaide（阿德莱德大学）；Beihang University（北京航空航天大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Australian National University（澳大利亚国立大学）
Institute of Information Science, Academia Sinica（中央研究院信息科学研究所）
YOLOv7 surpasses all known object detectors in both speed and accuracy in the range from 5 FPS to 160 FPS and has the highest accuracy 56.8% AP among all known real-time object detectors with 30 FPS or higher on GPU V100. YOLOv7-E6 object detector (56 FPS V100, 55.9% AP) outperforms both transformer-based detector SWIN-L Cascade-Mask R-CNN (9.2 FPS A100, 53.9% AP) by 509% in speed and 2% in accuracy, and convolutional-based detector ConvNeXt-XL Cascade-Mask R-CNN (8.6 FPS A100, 55.2% AP) by 551% in speed and 0.7% AP in accuracy, as well as YOLOv7 outperforms: YOLOR, YOLOX, Scaled-YOLOv4, YOLOv…
Although the YOLOv2 method is extremely fast on object detection, its detection accuracy is restricted due to the low performance of its backbone network and the underutilization of multi-scale region features. Therefore, a dense connection (DC) and spatial pyramid pooling (SPP) based YOLO (DC-SPP-YOLO) method for ameliorating the object detection accuracy of YOLOv2 is proposed in this paper. Specifically, the dense connection of convolution layers is employed in the backbone network of YOLOv2 to strengthen the feature extraction and alleviate the vanishing-gradient problem. Moreover, an impro…
Object Detection for Medical Image Analysis: Insights from the RT-DETR Model
University of California, Los Angeles（加州大学洛杉矶分校）；Duke University（杜克大学）；University of Massachusetts Boston（马萨诸塞大学波士顿分校）；University of Rochester（罗切斯特大学）；Northeastern University（东北大学）；Texas Tech University（德克萨斯理工大学）
Advanced Digital Sciences Center（先进数字科学中心）；Hamad Bin Khalifa University（哈马德·本·哈利法大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Performance of object detection models has been growing rapidly on two major fronts, model accuracy and efficiency. However, in order to map deep neural network (DNN) based object detection models to edge devices, one typically needs to compress such models significantly, thus compromising the model accuracy. In this paper, we propose a novel edge GPU friendly module for multi-scale feature interaction by exploiting missing combinatorial connections between various feature scales in existing state-of-the-art methods. Additionally, we propose a novel transfer learning backbone adoption inspired…
Detection of On-Ground Chestnuts Using Artificial Intelligence Toward Automated Picking
School of Automation Engineering, University of Electronic Science；Department of Biosystems \& Agricultural Engineering, Michigan State University, East Lansing, MI 48824, United States
YOLOv11-RGBT: Towards a Comprehensive Single-Stage Multispectral Object Detection Framework
School of Instrument Science and Opto-electronics Engineering, Anhui Province Key Laboratory of Measuring Theory and Precision Instrument（仪器科学与光电工程学院、安徽省测量理论与精密仪器重点实验室）；Hefei University of Technology（合肥工业大学）；School of Information Engineering（信息工程学院）；Engineering University of PAP（工程大学）
A Comparative Evaluation of Deep Learning Object Detection Models on a Real-World Multi-Plant Dataset from Africa
Bayero University（巴耶罗大学）；Alpen-Adria-Universität Klagenfurt（克拉根福阿尔卑斯-亚得里亚大学）；Gombe State University（贡贝州立大学）；Aliko Dangote University of Science and Technology（阿里科·丹格特科技大学）；Ahmadu Bello University（艾哈迈杜·贝洛大学）；Federal University Dutse（杜塞联邦大学）
Resource-Constrained UAV-Based Weed Detection for Site-Specific Management on Edge Devices
Department of Agricultural and Biological Engineering, Mississippi State University, Mississippi State, MS, USA（农业与生物工程系，密苏里州立大学）；Sustainable Agriculture Research Unit, Mississippi State, MS, USA（可持续农业研究单位，密苏里州）；Department of Plant and Soil Sciences, Mississippi State University, Mississippi State, MS, USA（植物与土壤科学系，密苏里州立大学）；Biosystems Engineering, North Dakota State University, Fargo, ND, USA（生物系统工程系，北达科塔州立大学）；NDSU Peltier Institute for the Advancement of Agricultural Technology, North Dakota State University, Fargo, ND, USA（NDSU裴特里农业技术进步研究所，北达科塔州立大学）
Replication Study and Benchmarking of Real-Time Object Detection Models
Département de physique, de génie physique et d’optique, Université Laval（物理、物理工程与光学系，拉瓦尔大学）；Département de génie électrique et de génie informatique, Université Laval（电气工程与计算机工程系，拉瓦尔大学）；Département d’informatique et de génie logiciel, Université Laval（计算机科学与软件工程系，拉瓦尔大学）
OV-DEIM: Real-time DETR-Style Open-Vocabulary Object Detection with GridSynthetic Augmentation
Intellindust AI Lab（Intellindust AI实验室）；Guangdong Laboratory of Artificial Intelligence（广东人工智能实验室）；College of Computer Science（计算机科学学院）；Software Engineering, Shenzhen University, China（软件工程，深圳大学，中国）；School of Information Technology, Carleton University, Canada（信息科技学院，卡尔顿大学，加拿大）；Institute for Research in Biomedicine, Bellinzona, Switzerland（生物医学研究 institute，贝尔林扎，瑞士）
USU-Corn-WeedDB: A UAV RGB Image Dataset for Multi-Species Weed Detection in Forage Corn
Department of Applied Sciences, Technology, and Education, Utah State University（应用科学、技术和教育系，犹他州立大学）；Department of Plants, Soils & Climate, Utah State University（植物、土壤与气候系，犹他州立大学）；Department of Civil and Environmental Engineering, Utah State University（土木与环境工程系，犹他州立大学）
