YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

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.

Automated summary

Real-time object detection is an important research topic in computer vision, and the development of new approaches in architecture optimization and training optimization has led to two related research topics. To address these topics, a trainable solution combining flexible and efficient training tools, proposed architecture, and compound scaling method is proposed. YOLOv7 outperforms all known object detectors in terms of speed and accuracy, achieving the highest AP accuracy of 56.8% among real-time object detectors with 30 FPS or higher on GPU V100.