EUVIMEDEUVIMED entdecken
Crossref

Bi-Directional and Triangular Circulation Fusion Neural Networks for Small Object Detection

Fangyu Li, Junzhu Duan, Qiyu Zhang, Caifeng Shan, Honggui Han

IEEE Transactions on Circuits and Systems for Video Technology · 2025-06 · 35 (6) · 5140-5152

DOI: 10.1109/tcsvt.2024.3523923 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-06. Verfasst von Fangyu Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: National Key Research and Development Project, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning-driven object detection models are capable of accurately identifying and localizing objects. However, small objects contain limited information relative to global features, resulting in the fact that detection models often do not learn small object features adequately. To enhance the precision in detecting small objects, we propose a bi-directional and triangular circulation fusion neural network (BTFN). First, to selectively strengthen the position features of small objects, we propose a feature circulation extraction module composed of a bi-directional triangular densely nested convolutional network (BTF), thus achieving repetitive multi-layer feature fusion. Second, to fill up the semantic gaps between different scales of features, we design a mixed dual attention module (MDA) in the bi-directional triangular densely nested network. Third, to mitigate the lost information in the neural networks with deep layers as well as improve the inference time, we design a re-parameterization bi-directional composite feature fusion module (Rep-BFM) that fuses the features of multiple scales. The proposed model is evaluated extensively on the MS COCO, Tsinghua-Tencent 100k, and Haier dismantled parts of used home appliances datasets. The experiment results show that the proposed model improves the AP on MS COCO by 4%, especially the APS of small objects is improved by 7.7% compared with SOTA models.

Förderung

  • National Key Research and Development Project
  • National Natural Science Foundation of China

Zitieren

APA

Li, F., Duan, J., Zhang, Q., Shan, C., & Han, H. (2025). Bi-Directional and Triangular Circulation Fusion Neural Networks for Small Object Detection. IEEE Transactions on Circuits and Systems for Video Technology, 35(6), 5140-5152. https://doi.org/10.1109/tcsvt.2024.3523923

Vancouver

Li F, Duan J, Zhang Q, Shan C, Han H. Bi-Directional and Triangular Circulation Fusion Neural Networks for Small Object Detection. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(6):5140-5152. doi:10.1109/tcsvt.2024.3523923

BibTeX
@article{Li2025,
  author = {Li, Fangyu and Duan, Junzhu and Zhang, Qiyu and Shan, Caifeng and Han, Honggui},
  title = {Bi-Directional and Triangular Circulation Fusion Neural Networks for Small Object Detection},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2025},
  volume = {35},
  number = {6},
  pages = {5140--5152},
  doi = {10.1109/tcsvt.2024.3523923}
}
Kostenlos starten →