Paper Reading AI Learner

Bridging the Scale Gap: Balanced Tiny and General Object Detection in Remote Sensing Imagery

2025-12-01 13:36:09
Zhicheng Zhao, Yin Huang, Lingma Sun, Chenglong Li, Jin Tang

Abstract

Tiny object detection in remote sensing imagery has attracted significant research interest in recent years. Despite recent progress, achieving balanced detection performance across diverse object scales remains a formidable challenge, particularly in scenarios where dense tiny objects and large objects coexist. Although large foundation models have revolutionized general vision tasks, their application to tiny object detection remains unexplored due to the extreme scale variation and density distribution inherent to remote sensing imagery. To bridge this scale gap, we propose ScaleBridge-Det, to the best of our knowledge, the first large detection framework designed for tiny objects, which could achieve balanced performance across diverse scales through scale-adaptive expert routing and density-guided query allocation. Specifically, we introduce a Routing-Enhanced Mixture Attention (REM) module that dynamically selects and fuses scale-specific expert features via adaptive routing to address the tendency of standard MoE models to favor dominant scales. REM generates complementary and discriminative multi-scale representations suitable for both tiny and large objects. Furthermore, we present a Density-Guided Dynamic Query (DGQ) module that predicts object density to adaptively adjust query positions and numbers, enabling efficient resource allocation for objects of varying scales. The proposed framework allows ScaleBridge-Det to simultaneously optimize performance for both dense tiny and general objects without trade-offs. Extensive experiments on benchmark and cross-domain datasets demonstrate that ScaleBridge-Det achieves state-of-the-art performance on AI-TOD-V2 and DTOD, while exhibiting superior cross-domain robustness on VisDrone.

Abstract (translated)

近年来,遥感图像中的微小目标检测引起了广泛的研究兴趣。尽管在这一领域取得了显著进展,但在密集型微小物体和大型物体共存的情况下实现各种尺度上的均衡检测性能仍是一项艰巨的挑战。虽然大规模基础模型已经革新了一般视觉任务,但由于遥感影像中极端的比例变化及密度分布特性,这类模型尚未被应用于微小目标检测。为了弥合这一比例差距,我们提出了ScaleBridge-Det——据我们所知,这是第一个专为微小对象设计的大规模检测框架。该框架通过尺度自适应专家路由和密度引导查询分配来实现各种尺度上的均衡性能。 具体来说,我们引入了增强型混合注意力(REM)模块,该模块能动态选择并融合特定尺度的专家特征,以解决标准MoE模型倾向于青睐主导比例的问题。REM生成适用于微小和大型物体的互补且具有区分性的多尺度表示形式。此外,我们还提出了密度引导动态查询(DGQ)模块,它预测目标密度,并据此自适应调整查询的位置和数量,从而为不同规模的对象高效地分配资源。 所提出的框架使ScaleBridge-Det能够同时优化密集型微小物体和一般对象的性能,而无需进行取舍。在基准数据集及跨域数据集上的广泛实验表明,ScaleBridge-Det在AI-TOD-V2和DTOD上实现了最新的性能,并且在VisDrone数据集中展示了优异的跨领域鲁棒性。

URL

https://arxiv.org/abs/2512.01665

PDF

https://arxiv.org/pdf/2512.01665.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