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

🤖 Plain-English Summary

Real-time object detection is one of the most important research topics in computer vision. 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.

🔑 Key Findings

• 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 advanced 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.

🔗 Related Resources