YOLOv10: Real-Time End-to-End Object Detection
Explore this paper's citation graph
Summary
A new generation of YOLO series for real-time end-to-end object detection, dubbed YOLOv10, is presented and the holistic efficiency-accuracy driven model design strategy for YOLOs is introduced, which greatly reduces the computational overhead and enhances the capability.
- Type
- preprint
- Published
- 2024-05-23
- Cited by
- 5,646
- References
- 82
- Access
- Open access
- OpenAlex
- https://openalex.org/W4398810114
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:269983404
Keywords
End-to-end principle, Computer science, Dead end, Object (grammar), Artificial intelligence
References
- End-to-End People Detection in Crowded Scenes
- You Only Look Once: Unified, Real-Time Object Detection
- Xception: Deep Learning with Depthwise Separable Convolutions
- Understanding the Effective Receptive Field in Deep Convolutional Neural Networks
- YOLO9000: Better, Faster, Stronger
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Learning Non-maximum Suppression
- YOLOv3: An Incremental Improvement
- MobileNetV2: Inverted Residuals and Linear Bottlenecks
- Statistical Aspects of Wasserstein Distances
- CenterNet: Keypoint Triplets for Object Detection
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Focal Loss for Dense Object Detection
- mixup: Beyond Empirical Risk Minimization
- Path Aggregation Network for Instance Segmentation
- Relation Networks for Object Detection
- Objects365: A Large-Scale, High-Quality Dataset for Object Detection
- Mobile Robot Navigation Using an Object Recognition Software with RGBD Images and the YOLO Algorithm
- Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
- CSPNet: A New Backbone that can Enhance Learning Capability of CNN
Cited by
- Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO
- ZeroReg: Zero-Shot Point Cloud Registration with Foundation Models
- CFMW: Cross-Modality Fusion Mamba for Robust Object Detection Under Adverse Weather
- SSGA-Net: Stepwise Spatial Global-local Aggregation Networks for for Autonomous Driving
- Immunocto: a massive immune cell database auto-generated for histopathology
- LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection
- Mamba YOLO: SSMs-Based YOLO For Object Detection
- Enhanced Object Detection: A Study on Vast Vocabulary Object Detection Track for V3Det Challenge 2024
- YOLOv1 to YOLOv10: A comprehensive review of YOLO variants and their application in the agricultural domain
- An Improved YOLOv8 Network for Detecting Electric Pylons Based on Optical Satellite Image
- LeYOLO, New Embedded Architecture for Object Detection
- A Study on Data Selection for Object Detection in Various Lighting Conditions for Autonomous Vehicles
- Fire-RPG: An Urban Fire Detection Network Providing Warnings in Advance
- In-Depth Review of YOLOv1 to YOLOv10 Variants for Enhanced Photovoltaic Defect Detection
- Automated anomaly detection of catenary split pins using unsupervised learning
- A fine-grained dataset for sewage outfalls objective detection in natural environments
- Transformer Discharge Carbon-Trace Detection Based on Improved MSRCR Image-Enhancement Algorithm and YOLOv8 Model
- A Real-Time Automatic Structural-Loss Detection and Stopping Rule of Semiconductor Single-Crystal-Silicon-Growth and
- SH17: A Dataset for Human Safety and Personal Protective Equipment Detection in Manufacturing Industry
- Towards Reflected Object Detection: A Benchmark
Related papers
- Does End-to-End Trained Deep Model Always Perform Better than Non-End-to-End Counterpart?
- Social Science at the Crossroads: Dead-End or Light at the End of a Dark Lane?
- Beginning with the End (of End-of-Life Law) in Mind
- End-to-End音声合成を用いた単語単位End-to-End音声認識のデータ拡張
- Exploring the performance benefits of end-to-end path switching
- End-to-end consensus using end-to-end channels
- Sub-modeling을 이용한 end-to-end 문합의 비선형 해석 ( Nonlinear Analysis of End-to-End Anastomosis Using Sub-modeling )