· 2023
YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors
- 11,163citations
- 2023year
Short summary
YOLOv7 achieves state-of-the-art real-time object detection by combining a trainable bag-of-freebies, architectural improvements, and compound scaling, outperforming all known detectors in speed and accuracy.
AI-generated from the title and abstract; the full text is not read.
Key points
- YOLOv7 introduces a trainable 'bag-of-freebies' for object detection training.
- It combines architectural optimizations and compound scaling with the new training tools.
- YOLOv7 achieves state-of-the-art accuracy (56.8% AP) at 30 FPS on GPU V100.
- It outperforms all known object detectors in speed across the 5-120 FPS range.
AI-generated from the title and abstract; the full text is not read.
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.
The authors' abstract, as published at the source., 2023 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionComputer Science