Edge-Constrained UAV Small-Object Detection with P2 Enhancement and Quantum-Inspired Lightweight Structure Search
2026-06-08 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors studied how to improve small-object detection in drones using lightweight object detectors. They enhanced a model called YOLOX-Nano by adding a high-resolution detection layer (P2) which helped detect small objects better without much extra cost. They also used a quantum-inspired evolutionary algorithm (QIEA) to find efficient model designs that balance accuracy, speed, and memory use. Tests showed their P2 addition significantly improved detection accuracy on a drone dataset, and QIEA helped select good model variants. However, the best candidates on quick tests didn’t always perform best after full training, highlighting the importance of thorough evaluation.
UAVobject detectionYOLOX-Nanosmall-object detectiondownsamplingP2 detection branchquantum-inspired evolutionary algorithmlightweight networksaccuracy-latency tradeoffVisDrone dataset
Authors
Wuming Lei, Yanbin Gao, Mingyan Sun, Xiaobin Li, Xuechen Liang
Abstract
Unmanned aerial vehicle (UAV) object detection requires compact detectors that retain small-object details under onboard computation and memory constraints. Repeated downsampling inlightweight networks weakens shallow spatial information, while manually adding attention orfusion modules may increase cost without stable gains. This study analyzes YOLOX-Nano underedge-deployment constraints by combining a P2 high-resolution detection branch with a quantum-inspired evolutionary algorithm (QIEA) for lightweight structure screening. The search space isdefined by lightweight priority and task specificity, and the evaluation jointly considers accuracy,floating-point operations (FLOPs), latency, memory consumption, and recall. On VisDrone, theP2 branch increases APamall by 31.10% over the YOLOX-Nano baseline. Compared with NanoDet-Plus with similar model size, YOLOX-Nano+-P2 improves APs0.ss by 17.5% and APamal by 44.9%.The QIEA-selected candidate obtains the highest Recallso, but +P2 remains the strongest AP-oriented variant after full training. Full 100-epoch verification of Random-best, GA-best, andSA/QUBO-best candidates further shows that proxy rankings do not necessarily transfer to finalAPse9s. These results support using P2 as the main small-object enhancement path and QIEA as alightweight tool for candidate screening and accuracy-cost analysis. The source code, configurationfiles, diagnostic scripts, and summarized results are available at https://github.com/Ming23233/UAV-QIEA-Edge-Detection