迈向高性能目标检测器：基于ViT与CNN深度学习模型的无人机检测洞见
Towards a High-Performance Object Detector: Insights from Drone Detection Using ViT and CNN-based Deep Learning Models
AI总结：
本文基于1359张无人机照片数据集，对比ViT与CNN检测模型，发现ViT在单机和多机检测中性能更强但资源需求更高，为高效目标检测器设计提供洞见。
摘要：
准确的无人机检测在无人机避碰、无人机防御以及自主无人飞行器（UAV）自主着陆中具有强烈需求。随着视觉Transformer（ViT）的近期出现，本文使用一个由1359张无人机照片组成的UAV数据集重新评估了这一关键任务。我们构建了多种CNN和基于ViT的模型，结果表明，在单无人机检测中，基础ViT的性能比我们最佳的基于CNN的迁移学习模型鲁棒4.6倍。通过在多无人机检测中实现最先进的You Only Look Once（YOLO v7，200个epoch）和实验性的基于ViT的You Only Look At One Sequence（YOLOS，20个epoch），我们分别取得了令人印象深刻的98%和96%的mAP值。我们发现，在相同epoch下，ViT优于CNN，但同时也需要更多的训练数据、计算能力以及复杂的、面向性能的设计，才能完全超越前沿CNN检测器的能力。我们总结了ViT和CNN模型的显著特征，以帮助未来研究人员开发更高效的深度学习模型。
英文摘要：
Accurate drone detection is strongly desired in drone collision avoidance, drone defense and autonomous Unmanned Aerial Vehicle (UAV) self-landing. With the recent emergence of the Vision Transformer (ViT), this critical task is reassessed in this paper using a UAV dataset composed of 1359 drone photos. We construct various CNN and ViT-based models, demonstrating that for single-drone detection, a basic ViT can achieve performance 4.6 times more robust than our best CNN-based transfer learning models. By implementing the state-of-the-art You Only Look Once (YOLO v7, 200 epochs) and the experimental ViT-based You Only Look At One Sequence (YOLOS, 20 epochs) in multi-drone detection, we attain impressive 98% and 96% mAP values, respectively. We find that ViT outperforms CNN at the same epoch, but also requires more training data, computational power, and sophisticated, performance-oriented designs to fully surpass the capabilities of cutting-edge CNN detectors. We summarize the distinct characteristics of ViT and CNN models to aid future researchers in developing more efficient deep learning models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
