CLSC DETR：基于跨层几何支持的可靠候选排序用于无人机小目标检测

中文摘要 AI 辅助

无人机（UAV）目标检测对目标搜索等应用至关重要，但在复杂空中场景中准确检测小目标仍具挑战性。小目标空间范围有限、分布密集且频繁被遮挡，使得可靠的候选排序尤为困难。现有的基于检测Transformer（DETR）的方法通过从单个查询估计定位质量并将其纳入分类分数来改进排序。然而，对于边界线索微弱的小目标，单个查询往往缺乏足够的几何证据，导致质量估计不可靠且排序不稳定。为解决这一局限，我们提出了用于DETR的跨层局部支持与一致性校准方法，即CLSC DETR。具体而言，跨层局部支持模块建立了最终层查询与中间层候选之间的对应关系，以聚合互补的几何证据，从而实现更可靠的定位质量估计；而分类与定位一致性校准模块则根据定位质量和分类可靠性自适应调整分类分数，以改进候选排序。实验表明，CLSC DETR在VisDrone数据集上较基线分别提升了1.5%的AP和2.0%的AP₇₅，同时在UAVDT数据集上也取得了一致的改进。

英文摘要

Unmanned aerial vehicle (UAV) object detection is critical for applications such as target search, where accurate detection of small objects in complex aerial scenes remains challenging. The limited spatial extent, dense distribution, and frequent occlusion of small objects make reliable candidate ranking particularly difficult. Existing Detection Transformer (DETR) based methods improve ranking by estimating localization quality from individual queries and incorporating it into classification scores. However, a single query often lacks sufficient geometric evidence for small objects with weak boundary cues, resulting in unreliable quality estimation and unstable ranking. To address this limitation, we propose Cross Layer Local Support and Consistency Calibration for DETR, termed CLSC DETR. Specifically, the Cross Layer Local Support module establishes correspondences between final layer queries and intermediate layer candidates to aggregate complementary geometric evidence for more reliable localization quality estimation, while the Classification and Localization Consistency Calibration module adaptively adjusts classification scores according to localization quality and classification reliability to improve candidate ranking. Experiments show that CLSC DETR improves AP and AP$_{75}$ over the baseline by 1.5\% and 2.0\% on VisDrone, respectively, while achieving consistent improvements on UAVDT.

发表机构

• South China Agricultural University（华南农业大学）

机构由 AI 辅助整理，请以论文原文为准。