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.

翻译：无人机精准检测在无人机避障、无人机防御及自主无人飞行器（UAV）自着陆中具有迫切需求。随着视觉Transformer（ViT）的近期兴起，本文利用由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ViT模型，证明在单无人机检测中，基础ViT模型的鲁棒性表现比我们最优的基于CNN的迁移学习模型高出4.6倍。通过在多无人机检测中应用最先进的You Only Look Once（YOLO v7，200轮）和基于ViT的实验性模型You Only Look At One Sequence（YOLOS，20轮），我们分别获得了令人瞩目的98%和96%的mAP值。我们发现ViT在相同训练轮次下优于CNN，但需要更多训练数据、计算算力及复杂且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与CNN模型的独特特征，以帮助未来研究者开发更高效的深度学习模型。