Paper Reading AI Learner

Cross-Modal Enhancement and Benchmark for UAV-based Open-Vocabulary Object Detection

2025-09-07 10:59:02
Zhenhai Weng, Zhongliang Yu

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

PDF

https://arxiv.org/pdf/2509.06011.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model LLM Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Robot Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Time_Series Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot