D3R-DETR: DETR with Dual-Domain Density Refinement for Tiny Object Detection in Aerial Images

2026-01-06

arXiv.org

AI Summary

This work addresses the challenges of detecting tiny objects in aerial imagery—such as sparse pixel representation, large density variations, slow convergence, and inaccurate query-object matching—by proposing D³R-DETR. The method introduces, for the first time, a dual-domain (spatial and frequency) density refinement mechanism into the DETR framework. By fusing and optimizing low-level features in both domains, it generates high-fidelity object density maps that guide query initialization and feature learning. Experiments on the AI-TOD-v2 dataset demonstrate that D³R-DETR significantly outperforms state-of-the-art approaches, achieving substantial improvements in both detection accuracy and localization performance for tiny objects.

Technology Category

• Computer Vision: Object Detection & Categorization
• Search and Optimization: Learning to Search
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Detecting tiny objects plays a vital role in remote sensing intelligent interpretation, as these objects often carry critical information for downstream applications. However, due to the extremely limited pixel information and significant variations in object density, mainstream Transformer-based detectors often suffer from slow convergence and inaccurate query-object matching. To address these challenges, we propose D$^3$R-DETR, a novel DETR-based detector with Dual-Domain Density Refinement. By fusing spatial and frequency domain information, our method refines low-level feature maps and utilizes their rich details to predict more accurate object density map, thereby guiding the model to precisely localize tiny objects. Extensive experiments on the AI-TOD-v2 dataset demonstrate that D$^3$R-DETR outperforms existing state-of-the-art detectors for tiny object detection.

Problem

• tiny object detection
• aerial images
• object density variation
• limited pixel information
• query-object matching

Innovation

• Dual-Domain Density Refinement
• Tiny Object Detection
• DETR
• Aerial Images
• Frequency-Spatial Fusion