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...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 7464 - 7475
Hlavní autoři: Wang, Chien-Yao, Bochkovskiy, Alexey, Liao, Hong-Yuan Mark
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2023
Témata:
Computer architecture
Computer vision
detection
Detectors
Object detection
Real-time systems
Recognition: Categorization
retrieval
Source coding
Training
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
ISSN:1063-6919
DOI:10.1109/CVPR52729.2023.00721