Small Object Detection by Synchronous Attention Swin Transformer with Channel Granularity Adaptive Mechanism
International Journal of Computational Intelligence Systems · 10.10.2025 · 18 (1)
DOI: 10.1007/s44196-025-00982-6 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Computational Intelligence Systems, online erschienen am 10.10.2025. Verfasst von Keping Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 75 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Youth Innovation Promotion Association of the Chinese Academy of Sciences, Natural Science Basic Research Program of Shaanxi Province.
Abstract (Originalsprache)
The essence of small object detection is to establish a mapping from the image pixels to the location and classification of targets. It is well known that a few valid pixels and complex backgrounds are the greatest challenges. This is because the intricate mapping cannot be formulated in a small object pixel space while facing a huge disturbance produced by background pixel spaces. To address these issues, this paper proposes a novel small object detection network named synchronous attention granularity Swin Transformer (SAG-ST). A synchronous attention ST block is proposed to elegantly integrate information from deep and shallow features. And the granularity adaptive ST block employs a channel granularity adaptive mechanism to mitigate background interference by adaptively applying self-attention with varying granularities for different channels. Finally, this paper creates a small object detection dataset based on unmanned aerial vehicles with different flight altitudes. The experiments are carried out on the created dataset and VisDrone dataset, and the experimental results show that our SAG-ST algorithm achieves the best detection accuracy.
Förderung
- Youth Innovation Promotion Association of the Chinese Academy of Sciences
- Natural Science Basic Research Program of Shaanxi Province
Zitieren
APA
Wang, K., Suo, B., Qian, W., Zhang, G., Wang, T., & Yang, Y. (2025). Small Object Detection by Synchronous Attention Swin Transformer with Channel Granularity Adaptive Mechanism. International Journal of Computational Intelligence Systems, 18(1). https://doi.org/10.1007/s44196-025-00982-6
Vancouver
Wang K, Suo B, Qian W, Zhang G, Wang T, Yang Y. Small Object Detection by Synchronous Attention Swin Transformer with Channel Granularity Adaptive Mechanism. International Journal of Computational Intelligence Systems. 2025;18(1). doi:10.1007/s44196-025-00982-6
BibTeX
@article{Wang2025,
author = {Wang, Keping and Suo, Bingqian and Qian, Wei and Zhang, Gaopeng and Wang, Tian and Yang, Yi},
title = {Small Object Detection by Synchronous Attention Swin Transformer with Channel Granularity Adaptive Mechanism},
journal = {International Journal of Computational Intelligence Systems},
year = {2025},
volume = {18},
number = {1},
doi = {10.1007/s44196-025-00982-6}
}
EUVIMED