Dome-DETR: DETR with Density-Oriented Feature-Query Manipulation for Efficient Tiny Object Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913979602829312 |
|---|---|
| author | Hu, Zhangchi Wu, Peixi Chen, Jie Zhu, Huyue Wang, Yijun Peng, Yansong Li, Hebei Sun, Xiaoyan |
| author_facet | Hu, Zhangchi Wu, Peixi Chen, Jie Zhu, Huyue Wang, Yijun Peng, Yansong Li, Hebei Sun, Xiaoyan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_05741 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dome-DETR: DETR with Density-Oriented Feature-Query Manipulation for Efficient Tiny Object Detection Hu, Zhangchi Wu, Peixi Chen, Jie Zhu, Huyue Wang, Yijun Peng, Yansong Li, Hebei Sun, Xiaoyan Computer Vision and Pattern Recognition 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. |
| title | Dome-DETR: DETR with Density-Oriented Feature-Query Manipulation for Efficient Tiny Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.05741 |