EUVIMEDEUVIMED entdecken
Crossref

Low-Resolution Self-Attention for Semantic Segmentation

Yu-Huan Wu, Shi-Chen Zhang, Yun Liu, Le Zhang, Xin Zhan, Daquan Zhou, Jiashi Feng, Ming-Ming Cheng, Liangli Zhen

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-09 · 47 (9) · 8180-8192

DOI: 10.1109/tpami.2025.3577035 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-09. Verfasst von Yu-Huan Wu und 8 weiteren Autor:innen. Die Arbeit wurde bisher 35-mal zitiert (Crossref) und nennt 96 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities, Nankai University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Semantic segmentation tasks naturally require high-resolution information for pixel-wise segmentation and global context information for class prediction. While existing vision transformers demonstrate promising performance, they often utilize high-resolution context modeling, resulting in a computational bottleneck. In this work, we challenge conventional wisdom and introduce the Low-Resolution Self-Attention (LRSA) mechanism to capture global context at a significantly reduced computational cost, i.e., FLOPs. Our approach involves computing self-attention in a fixed low-resolution space, regardless of the input image's resolution, with additional $\text{3}\times \text{3}$3×3 depth-wise convolutions to capture fine details in the high-resolution space. We demonstrate the effectiveness of our LRSA approach by building the LRFormer, a vision transformer with an encoder-decoder structure. Extensive experiments on the ADE20 K, COCO-Stuff, and CityScapes datasets demonstrate that LRFormer outperforms state-of-the-art models.

Förderung

  • National Natural Science Foundation of China
  • Fundamental Research Funds for the Central Universities
  • Nankai University
  • A*STAR Career Development Fund
  • National Research Foundation Singapore
  • AI Singapore Programme
  • Supercomputing Center of Nankai University

Zitieren

APA

Wu, Y. H., Zhang, S. C., Liu, Y., Zhang, L., Zhan, X., Zhou, D., Feng, J., Cheng, M. M., & Zhen, L. (2025). Low-Resolution Self-Attention for Semantic Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(9), 8180-8192. https://doi.org/10.1109/tpami.2025.3577035

Vancouver

Wu YH, Zhang SC, Liu Y, Zhang L, Zhan X, Zhou D, et al. Low-Resolution Self-Attention for Semantic Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(9):8180-8192. doi:10.1109/tpami.2025.3577035

BibTeX
@article{Wu2025,
  author = {Wu, Yu-Huan and Zhang, Shi-Chen and Liu, Yun and Zhang, Le and Zhan, Xin and Zhou, Daquan and Feng, Jiashi and Cheng, Ming-Ming and Zhen, Liangli},
  title = {Low-Resolution Self-Attention for Semantic Segmentation},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {9},
  pages = {8180--8192},
  doi = {10.1109/tpami.2025.3577035}
}
Kostenlos starten →