Dome-DETR: DETR with Density-Oriented Feature-Query Manipulation for Efficient Tiny Object Detection

TL;DR

Dome-DETR introduces a density-oriented feature-query manipulation framework that enhances tiny object detection efficiency by reducing redundancy, focusing attention, and adaptively allocating queries, achieving state-of-the-art results with low computational cost.

Contribution

The paper presents Dome-DETR, a novel framework with density-oriented feature-query manipulation, including a lightweight extractor, sparse attention, and adaptive query initialization for efficient tiny object detection.

Findings

Achieves +3.3 AP on AI-TOD-V2

Achieves +2.5 AP on VisDrone

Maintains low computational complexity and model size

Abstract

Tiny object detection plays a vital role in drone surveillance, remote sensing, and autonomous systems, enabling the identification of small targets across vast landscapes. However, existing methods suffer from inefficient feature leverage and high computational costs due to redundant feature processing and rigid query allocation. To address these challenges, we propose Dome-DETR, a novel framework with Density-Oriented Feature-Query Manipulation for Efficient Tiny Object Detection. To reduce feature redundancies, we introduce a lightweight Density-Focal Extractor (DeFE) to produce clustered compact foreground masks. Leveraging these masks, we incorporate Masked Window Attention Sparsification (MWAS) to focus computational resources on the most informative regions via sparse attention. Besides, we propose Progressive Adaptive Query Initialization (PAQI), which adaptively modulates query density across spatial areas for better query allocation. Extensive experiments demonstrate that Dome-DETR achieves state-of-the-art performance (+3.3 AP on AI-TOD-V2 and +2.5 AP on VisDrone) while maintaining low computational complexity and a compact model size. Code is available at https://github.com/RicePasteM/Dome-DETR.