Small-Object Detection at the Edge: A Pareto-Efficient Benchmark of Lightweight YOLO Models on UAV and Overhead Datasets
TL;DR
This article benchmarks lightweight YOLO models for small-object detection in UAV and overhead datasets, emphasizing Pareto efficiency to balance accuracy, latency, and energy for edge deployment.
Small-Object Detection at the Edge: A Pareto-Efficient Benchmark of Lightweight YOLO Models on UAV and Overhead Datasets
Bijay Shakya; Omar El-Gayar; Jihene Kaabi; Khandaker Mamun Ahmed
https://doi.org/10.1109/ACCESS.2025.3648968
Volume 14
Small-object detection plays a critical role in real-time aerial, Uncrewed Aerial Vehicle (UAV), and satellite vision systems, as well as many other domains, where hardware constraints and deployment environments demand high accuracy, low latency, and energy efficiency. Although numerous lightweight object detectors have been proposed, there exists a lack of rigorous, cross-platform benchmarks tha...