EUVIMEDEUVIMED entdecken
Crossref

StructToken: Rethinking Semantic Segmentation With Structural Prior

Fangjian Lin, Zhanhao Liang, Sitong Wu, Junjun He, Kai Chen, Shengwei Tian

IEEE Transactions on Circuits and Systems for Video Technology · 2023-10 · 33 (10) · 5655-5663

DOI: 10.1109/tcsvt.2023.3252807 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2023-10. Verfasst von Fangjian Lin und 5 weiteren Autor:innen. Die Arbeit wurde bisher 57-mal zitiert (Crossref) und nennt 57 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Xinjiang Autonomous Region Key Research and Development Project, Xinjiang Autonomous Region Major Scientific and Technological Projects.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In previous deep-learning-based methods, semantic segmentation has been regarded as a static or dynamic per-pixel classification task, i.e., classify each pixel representation to a specific category. However, these methods only focus on learning better pixel representations or classification kernels while ignoring the structural information of objects, which is critical to human decision-making mechanism. In this paper, we present a new paradigm for semantic segmentation, named structure-aware extraction. Specifically, it generates the segmentation results via the interactions between a set of learned structure tokens and the image feature, which aims to progressively extract the structural information of each category from the feature. Extensive experiments show that our StructToken outperforms the state-of-the-art on three widely-used benchmarks, including ADE20K, Cityscapes, and COCO-Stuff-10K.

Förderung

  • National Natural Science Foundation of China
  • Xinjiang Autonomous Region Key Research and Development Project
  • Xinjiang Autonomous Region Major Scientific and Technological Projects

Zitieren

APA

Lin, F., Liang, Z., Wu, S., He, J., Chen, K., & Tian, S. (2023). StructToken: Rethinking Semantic Segmentation With Structural Prior. IEEE Transactions on Circuits and Systems for Video Technology, 33(10), 5655-5663. https://doi.org/10.1109/tcsvt.2023.3252807

Vancouver

Lin F, Liang Z, Wu S, He J, Chen K, Tian S. StructToken: Rethinking Semantic Segmentation With Structural Prior. IEEE Transactions on Circuits and Systems for Video Technology. 2023;33(10):5655-5663. doi:10.1109/tcsvt.2023.3252807

BibTeX
@article{Lin2023,
  author = {Lin, Fangjian and Liang, Zhanhao and Wu, Sitong and He, Junjun and Chen, Kai and Tian, Shengwei},
  title = {StructToken: Rethinking Semantic Segmentation With Structural Prior},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2023},
  volume = {33},
  number = {10},
  pages = {5655--5663},
  doi = {10.1109/tcsvt.2023.3252807}
}
Kostenlos starten →