Real-time object detector YOLOv10 beats YOLOv9 in speed and size by consistent assignments
Real-time object detector YOLOv10 beats YOLOv9 in speed and size by consistent assignments
YOLOv10: Real-Time End-to-End Object Detection
arXiv paper abstract https://arxiv.org/abs/2405.14458
arXiv PDF paper https://arxiv.org/pdf/2405.14458
GitHub https://github.com/THU-MIG/yolov10
… YOLOs have emerged as the predominant paradigm in … real-time object detection owing to their effective balance between computational cost and detection performance.
… aim to further advance the performance-efficiency boundary of YOLOs from both the post-processing and model architecture.
… present the consistent dual assignments for NMS-free training of YOLOs, which brings competitive performance and low inference latency simultaneously.
… introduce the holistic efficiency-accuracy driven model design strategy for YOLOs.
… optimize … components of YOLOs from both efficiency and accuracy perspectives, which greatly reduces the computational overhead and enhances the capability.
… YOLOv10 achieves state-of-the-art … across … model scales … Compared with YOLOv9-C, YOLOv10-B has 46% less latency and 25% fewer parameters for the same performance.
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
