Tools
Tools
Yu, Boyang, Li, Zixuan, Cao, Yue, Zhang, Xu 
ORCID: https://orcid.org/0000-0001-6557-6607, Lim, Wansu and Liu, William
(2026)
A dual-path lightweight detector with hybrid attention for real-time object detection.
Engineering Applications of Artificial Intelligence, 176.
ISSN 0952-1976
Preview |
PDF (A Dual-path)
- Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (777kB) | Preview |
Abstract
Unmanned aerial vehicle (UAV)-based object detection presents significant challenges, including pronounced variations in object scale and limited computational resources. To address these issues, this paper proposes the Dual-path and Bimodal-attention-enhanced Network (DBYNet), a real-time detection framework optimized for UAV applications. DBYNet adopts a deployment-oriented design that integrates a dual-path backbone for spatial–semantic feature decoupling, a hybrid attention mechanism for enhanced contextual modeling, and lightweight optimization strategies to improve inference efficiency. Specifically, a shallow lightweight branch preserves fine-grained spatial details, while a deep branch with deformable convolutions captures high-level semantic features, and the proposed hybrid attention combines Overlapping Cross Attention (OCA) and Channel-spatial Bimodal Attention (CAB) to strengthen feature interaction. In addition, Quantization-Aware Training and temperature-aware distillation are employed to reduce model complexity without compromising accuracy. Extensive experiments on the VisDrone2019 dataset demonstrate that DBYNet achieves a favorable accuracy–efficiency trade-off, particularly improving robustness for small, densely distributed, and low-visibility targets in challenging UAV scenarios.
| Item Type: | Article |
|---|---|
| Additional Information: | Publisher Copyright: © 2026 Elsevier Ltd. |
| Uncontrolled Keywords: | attention mechanism,lightweight design,object detection,unmanned aerial vehicle imagery,control and systems engineering,electrical and electronic engineering,artificial intelligence ,/dk/atira/pure/subjectarea/asjc/2200/2207 |
| Faculty \ School: | Faculty of Science > School of Computing Sciences |
| Related URLs: | |
| Depositing User: | LivePure Connector |
| Date Deposited: | 18 Sep 2026 09:27 |
| Last Modified: | 20 Sep 2026 05:26 |
| URI: | https://ueaeprints.uea.ac.uk/id/eprint/104588 |
| DOI: | 10.1016/j.engappai.2026.114669 |
Downloads
Downloads per month over past year
Actions (login required)
 |
View Item |