EUVIMEDEUVIMED entdecken
Crossref

STDBNet: Shared Trunk and Dual-Branch Network for Real-Time Semantic Segmentation

Fenglei Ren, Haibo Zhou, Lu Yang, Yiwen Bai, Wenxue Xu

IEEE Signal Processing Letters · 2024 · 31 · 770-774

DOI: 10.1109/lsp.2023.3347144 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2024. Verfasst von Fenglei Ren und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 33 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Real-time semantic segmentation has broad prospects in computer vision. Existing state-of-the-art approaches generally employ bilateral networks to encode spatial and contextual information. Nevertheless, the real-time methods exhibit unsatisfactory performance. To address this problem, in this work we propose a novel shared trunk and dual-branch network named STDBNet for real-time semantic segmentation. In particular, we devise a Shared Trunk Module, which efficiently diminishes superfluous channels and parameters. Subsequently, we present a Split Dual-Branch Module, consisting of Detail Branch and Semantic Branch, with the former capturing detailed information and the latter capturing contextual information correspondingly. Furthermore, at the Semantic Branch, an Efficient Pyramid Pooling Module is designed towards the end to further expand the receptive fields and harvest multi-scale contextual information. Finally, to efficiently merge the features from the two branches and then get the final results, we introduce an Attention-optimized Feature Fusion Module, which utilizes redesigned spatial attention mechanism for feature augmentation. Extensive experiments conducted on the Cityscapes dataset indicate that the devised STDBNet obtains 77.6% mIoU with 91.5 FPS on one GeForce 2080Ti GPU, which outperforms BiSeNet with a favorable trade-off between accuracy and efficiency.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Ren, F., Zhou, H., Yang, L., Bai, Y., & Xu, W. (2024). STDBNet: Shared Trunk and Dual-Branch Network for Real-Time Semantic Segmentation. IEEE Signal Processing Letters, 31, 770-774. https://doi.org/10.1109/lsp.2023.3347144

Vancouver

Ren F, Zhou H, Yang L, Bai Y, Xu W. STDBNet: Shared Trunk and Dual-Branch Network for Real-Time Semantic Segmentation. IEEE Signal Processing Letters. 2024;31:770-774. doi:10.1109/lsp.2023.3347144

BibTeX
@article{Ren2024,
  author = {Ren, Fenglei and Zhou, Haibo and Yang, Lu and Bai, Yiwen and Xu, Wenxue},
  title = {STDBNet: Shared Trunk and Dual-Branch Network for Real-Time Semantic Segmentation},
  journal = {IEEE Signal Processing Letters},
  year = {2024},
  volume = {31},
  pages = {770--774},
  doi = {10.1109/lsp.2023.3347144}
}
Kostenlos starten →