YOLO Meets Mixture-of-Experts: Adaptive Expert Routing for Robust Object Detection
By: Ori Meiraz, Sharon Shalev, Avishai Weizman
Potential Business Impact:
Makes computer vision models smarter at spotting things.
This paper presents a novel Mixture-of-Experts framework for object detection, incorporating adaptive routing among multiple YOLOv9-T experts to enable dynamic feature specialization and achieve higher mean Average Precision (mAP) and Average Recall (AR) compared to a single YOLOv9-T model.
Similar Papers
YOLO Meets Mixture-of-Experts: Adaptive Expert Routing for Robust Object Detection
CV and Pattern Recognition
Makes computer vision models smarter at finding objects.
YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection
CV and Pattern Recognition
Lets computers see objects better by thinking smarter.
YOLOv1 to YOLOv11: A Comprehensive Survey of Real-Time Object Detection Innovations and Challenges
CV and Pattern Recognition
Helps computers see and understand things faster.