Abstract
Open-Vocabulary Object Detection (OVD) has emerged as a pivotal technology for applications involving Unmanned Aerial Vehicles (UAVs). However, the prevailing large-scale datasets for OVD pre-training are predominantly composed of ground-level, natural images. This creates a significant domain gap, causing models trained on them to exhibit a substantial drop in performance on UAV imagery. To address this limitation, we first propose a refined UAV-Label engine. Then we construct and introduce UAVDE-2M(contains over 2,000,000 instances and 1800 categories) and UAVCAP-15k(contains over 15,000 images). Furthermore, we propose a novel Cross-Attention Gated Enhancement Fusion (CAGE) module and integrate it into the YOLO-World-v2 architecture. Finally, extensive experiments on the VisDrone and SIMD datasets verify the effectiveness of our proposed method for applications in UAV-based imagery and remote sensing.
Abstract (translated)
开放词汇物体检测(OVD)已成为涉及无人驾驶航空器(UAVs)应用的关键技术。然而,现有的大规模数据集用于OVD预训练主要是地面自然图像为主的,这造成了显著的领域差距,导致在UAV图像上性能大幅下降。为解决这一局限性,我们首先提出了一种精炼的UAV-Label引擎。然后构建并介绍了包含超过2,000,000个实例和1800类别的UAVDE-2M数据集以及包含超过15,000张图像的UAVCAP-15k数据集。此外,我们还提出了一种新颖的跨注意力门控增强融合(CAGE)模块,并将其集成到YOLO-World-v2架构中。最后,在VisDrone和SIMD数据集上的广泛实验验证了我们的方法在基于UAV图像和远程传感应用中的有效性。
URL
https://arxiv.org/abs/2509.06011