A Paradigm Shift in Real-Time Detection: The YOLOv7 Approach to Trainable Freebie Optimization
A. Vinitha, S. R. Selva Jeevitha, Nikhil Kumar, Sathish Kumar L, D. Saravanan · 2025
Significant progress has been made in real-time object detection, with YOLOv7 emerging as a state-of-the-art model that achieves the highest levels of accuracy and speed. This study combines Bag-of-Freebies (BoF) strategies with YOLOv7 to improve performance without incurring extra computational expenses. Our tests show that adding BoF preserves real-time inference capabilities while increasing [email protected] by 3.5%. The accuracy and FPS of YOLOv7 with BoF are superior to those of the current YOLO-based models (YOLOv4, YOLOv5, YOLOv6). According to the results, YOLOv7 with BoF sets a new standard for real-time object detection by achieving a [email protected] of 55.3% and 83 FPS on the COCO dataset.