Concepedia

Publication | Closed Access

YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors

10.2K

Citations

74

References

2023

Year

TLDR

Real‑time object detection remains a critical computer‑vision challenge, with continual advances in architecture and training optimization driving new research directions. The authors propose a trainable bag‑of‑freebies framework to tackle these emerging research topics. They integrate flexible, efficient training tools with the new architecture and a compound scaling method. YOLOv7 outperforms all existing real‑time detectors, achieving 56.8 % AP at 30 FPS or higher on a V100 GPU while covering a speed range from 5 to 120 FPS. Source code is available at https://github.com/WongKinYiu/yolov7.

Abstract

Real-time object detection is one of the most important research topics in computer vision. As new approaches regarding architecture optimization and training optimization are continually being developed, we have found two research topics that have spawned when dealing with these latest state-of-the-art methods. To address the topics, we propose a trainable bag-of-freebies oriented solution. We combine the flexible and efficient training tools with the proposed architecture and the compound scaling method. YOLOv7 surpasses all known object detectors in both speed and accuracy in the range from 5 FPS to 120 FPS and has the highest accuracy 56.8% AP among all known real-time object detectors with 30 FPS or higher on GPU V100. Source code is released in https://github.com/WongKinYiu/yolov7.

References

YearCitations

Page 1