Paper#Computer Vision🔬 ResearchAnalyzed: Jan 3, 2026 16:09

YOLO-Master: Adaptive Computation for Real-time Object Detection

Published:Dec 29, 2025 07:54
1 min read
ArXiv

Analysis

This paper introduces YOLO-Master, a novel YOLO-like framework that improves real-time object detection by dynamically allocating computational resources based on scene complexity. The use of an Efficient Sparse Mixture-of-Experts (ES-MoE) block and a dynamic routing network allows for more efficient processing, especially in challenging scenes, while maintaining real-time performance. The results demonstrate improved accuracy and speed compared to existing YOLO-based models.

Reference

YOLO-Master achieves 42.4% AP with 1.62ms latency, outperforming YOLOv13-N by +0.8% mAP and 17.8% faster inference.