EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AeroPinWorld: Revisiting Stride-2 Downsampling for Zero-Shot Transferable Open-Vocabulary UAV Detection

Jie Li, Mingze Guan, Jincheng Xu, Xun Du, Haonan Chen, Yang Liu

Electronics · 25.03.2026 · 15 (7) · 1364

DOI: 10.3390/electronics15071364 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 25.03.2026. Verfasst von Jie Li und 5 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China https://ror.org/01h0zpd94, Anhui Province Key Laboratory of Machine Vision Detection and Perception, Anhui Province Key Laboratory of Special and Heavy Load Robot.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Open-vocabulary object detection in unmanned aerial vehicle (UAV) imagery remains challenging under zero-shot cross-dataset transfer because tiny and cluttered targets are highly sensitive to early resolution reduction under domain shift. This study aims to improve transferable open-vocabulary UAV detection by revisiting stride-2 downsampling in YOLO-World v2 as a transfer-critical bottleneck. AeroPinWorld is introduced as a pinwheel-augmented YOLO-World v2 that selectively replaces four key stride-2 transitions with pinwheel-shaped convolution (PConv) so as to reduce aliasing, alleviate sampling-phase sensitivity, and preserve fine-grained local structures, while keeping the original detection head unchanged to ensure a fair and efficient comparison. The model is trained on COCO2017 for 24 epochs from official pretrained weights and directly evaluated, without target-domain fine-tuning, on VisDrone2019-DET and UAVDT using fixed offline prompt vocabularies. Compared with YOLO-World v2-S, AeroPinWorld improves zero-shot transfer performance on VisDrone from 0.112 to 0.135 mAP and from 0.054 to 0.063 APS, and it also yields consistent gains on UAVDT. Ablation studies show that both early backbone replacements and head bottom–up replacements contribute to the final gains, with their combination achieving the best accuracy–efficiency trade-off. These results indicate that selectively redesigning transfer-critical downsampling operators is an effective and lightweight way to improve zero-shot open-vocabulary UAV detection under aerial domain shift.

Förderung

  • National Natural Science Foundation of China https://ror.org/01h0zpd94
  • Anhui Province Key Laboratory of Machine Vision Detection and Perception
  • Anhui Province Key Laboratory of Special and Heavy Load Robot
  • Fundamental Research Funds for the Central Universities, China

Zitieren

APA

Li, J., Guan, M., Xu, J., Du, X., Chen, H., & Liu, Y. (2026). AeroPinWorld: Revisiting Stride-2 Downsampling for Zero-Shot Transferable Open-Vocabulary UAV Detection. Electronics, 15(7), 1364. https://doi.org/10.3390/electronics15071364

Vancouver

Li J, Guan M, Xu J, Du X, Chen H, Liu Y. AeroPinWorld: Revisiting Stride-2 Downsampling for Zero-Shot Transferable Open-Vocabulary UAV Detection. Electronics. 2026;15(7):1364. doi:10.3390/electronics15071364

BibTeX
@article{Li2026,
  author = {Li, Jie and Guan, Mingze and Xu, Jincheng and Du, Xun and Chen, Haonan and Liu, Yang},
  title = {AeroPinWorld: Revisiting Stride-2 Downsampling for Zero-Shot Transferable Open-Vocabulary UAV Detection},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {7},
  pages = {1364},
  doi = {10.3390/electronics15071364}
}
Kostenlos starten →