AF-YOLO: Asymptotic Feature Extraction and Fusion for Aerial Object Detection
IEEE Transactions on Circuits and Systems for Video Technology · 2026-01 · 36 (1) · 63-78
DOI: 10.1109/tcsvt.2025.3595740 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-01. Verfasst von Lve Huang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 66 Literaturangaben. Gefördert von: Natural Science Foundation of Jiangxi Province, Key Research Project of Science and Technology by Jiangxi Provincial Department of Education, National Natural Science Foundation of China.
Abstract (Originalsprache)
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 mAP0.5 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.
Förderung
- Natural Science Foundation of Jiangxi Province
- Key Research Project of Science and Technology by Jiangxi Provincial Department of Education
- National Natural Science Foundation of China
- Beijing Natural Science Foundation
Zitieren
APA
Huang, L., Yu, X., Yan, H., Huang, L., An, Z., & Xu, Y. (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. https://doi.org/10.1109/tcsvt.2025.3595740
Vancouver
Huang L, Yu X, Yan H, Huang L, An Z, Xu Y. AF-YOLO: Asymptotic Feature Extraction and Fusion for Aerial Object Detection. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(1):63-78. doi:10.1109/tcsvt.2025.3595740
BibTeX
@article{Huang2026,
author = {Huang, Lve and Yu, Xiaowei and Yan, Huabiao and Huang, Libo and An, Zhulin and Xu, Yongjun},
title = {AF-YOLO: Asymptotic Feature Extraction and Fusion for Aerial Object Detection},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2026},
volume = {36},
number = {1},
pages = {63--78},
doi = {10.1109/tcsvt.2025.3595740}
}
EUVIMED