AF-YOLO: Asymptotic Feature Extraction and Fusion for Aerial Object Detection

doi:10.1109/TCSVT.2025.3595740

CSpace

	AF-YOLO: Asymptotic Feature Extraction and Fusion for Aerial Object Detection
	Huang, Lve 1; Yu, Xiaowei 1; Yan, Huabiao 1; Huang, Libo 2; An, Zhulin 2; Xu, Yongjun 2
	2026
发表期刊	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
ISSN	1051-8215
卷号	36 期号:1 页码:63-78
摘要	Aerial object detection plays a vital role in applications such as natural disaster prevention and urban traffic management, thanks to its ability to handle wide coverage areas and diverse objects. As a leading method for this task, You Only Look Once (YOLO) leverages multi-scale feature extraction to detect objects of various sizes. However, most YOLO-based methods focus on feature extraction and fusion from adjacent scales, neglecting the potential collaboration between non-adjacent scales. This limitation leads to redundant parameters and suboptimal detection performance. To address these issues, this paper proposes AF-YOLO (Asymptotic Feature Extraction and Fusion YOLO), a novel approach tailored for aerial object detection. AF-YOLO introduces two lightweight modules: SCC2f and PAFFN. SCC2f, an optimized version of cross-stage partial bottleneck with spatial and channel reconstruction convolution layers, reduces redundancy and enables efficient multi-scale feature extraction. PAFFN, a parallel asymptotic feature fusion network, facilitates enhanced interaction and fusion of non-adjacent scale features. Additionally, AF-YOLO incorporates a P2 layer to improve small object detection and removes YOLO's P5 layer for a more lightweight design, specifically optimized for aerial detection tasks. Experimental results demonstrate AF-YOLO's significant improvements across multiple benchmarks: on the VisDrone dataset, it achieves a 6.1% higher mAP(0.5) compared to recent baselines while using only 41.8% of their parameters; on the DIOR dataset, it shows a 3.3% accuracy improvement over YOLOv8. These quantitative results are further supported by its superior performance on the DOTA and FAIR1M datasets, with additional validation on HazyDet confirming its robustness in adverse weather conditions. Collectively, these achievements highlight AF-YOLO's exceptional generalization capability and efficient lightweight design, establishing a new state-of-the-art for aerial object detection systems.
关键词	Feature extraction YOLO Head Videos Convolution Accuracy Proposals Hands Fuses Training Aerial image object detection feature extraction asymptotic fusion lightweight model
DOI	10.1109/TCSVT.2025.3595740
收录类别	SCI
语种	英语
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:001673821800029
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42866
专题	中国科学院计算技术研究所
通讯作者	Huang, Libo
作者单位	1.Jiangxi Univ Sci & Technol, Jiangxi Prov Key Lab Multidimens Intelligent Perce, Ganzhou 341000, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Huang, Lve,Yu, Xiaowei,Yan, Huabiao,et al. AF-YOLO: Asymptotic Feature Extraction and Fusion for Aerial Object Detection[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2026,36(1):63-78.
APA	Huang, Lve,Yu, Xiaowei,Yan, Huabiao,Huang, Libo,An, Zhulin,&Xu, Yongjun.(2026).AF-YOLO: Asymptotic Feature Extraction and Fusion for Aerial Object Detection.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,36(1),63-78.
MLA	Huang, Lve,et al."AF-YOLO: Asymptotic Feature Extraction and Fusion for Aerial Object Detection".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 36.1(2026):63-78.