Detecting objects from Unmanned Aerial Vehicles (UAV) is often hindered by a large number of small objects, resulting in low detection accuracy. To address this issue, mainstream approaches typically utilize multi-stage inferences. Despite their remarkable detecting accuracies, real-time efficiency is sacrificed, making them less practical to handle real applications. To this end, we propose to improve the single-stage inference accuracy through learning scale-invariant features. Specifically, a Scale-Invariant Feature Disentangling module is designed to disentangle scale-related and scale-invariant features. Then an Adversarial Feature Learning scheme is employed to enhance disentanglement. Finally, scale-invariant features are leveraged for robust UAV-based object detection. Furthermore, we construct a multi-modal UAV object detection dataset, State-Air, which incorporates annotated UAV state parameters. We apply our approach to three state-of-the-art lightweight detection frameworks on three benchmark datasets, including State-Air. Extensive experiments demonstrate that our approach can effectively improve model accuracy. Our code and dataset are provided in Supplementary Materials and will be publicly available once the paper is accepted.

翻译：从无人机（UAV）检测目标常因存在大量小目标而受阻，导致检测精度低下。为解决此问题，主流方法通常采用多阶段推理。尽管这些方法具有显著的检测精度，但牺牲了实时效率，使其在处理实际应用时实用性不足。为此，我们提出通过学习尺度不变特征来提高单阶段推理的精度。具体而言，我们设计了一个尺度不变特征解耦模块，用于解耦尺度相关特征与尺度不变特征。随后采用对抗特征学习方案以增强解耦效果。最后，利用尺度不变特征实现鲁棒的无人机目标检测。此外，我们构建了一个多模态无人机目标检测数据集State-Air，该数据集包含了标注的无人机状态参数。我们将所提方法应用于三种最先进的轻量级检测框架，并在三个基准数据集（包括State-Air）上进行了验证。大量实验表明，我们的方法能有效提升模型精度。我们的代码与数据集已提供在补充材料中，并将在论文录用后公开。