EUVIMEDEUVIMED entdecken
Crossref

Spike2Former: Efficient Spiking Transformer for High-performance Image Segmentation

Zhenxin Lei, Man Yao, Jiakui Hu, Xinhao Luo, Yanye Lu, Bo Xu, Guoqi Li

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (2) · 1364-1372

DOI: 10.1609/aaai.v39i2.32126 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Zhenxin Lei und 6 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Spiking Neural Networks (SNNs) have a low-power advantage but perform poorly in image segmentation tasks. The reason is that directly converting neural networks with complex architectural designs for segmentation tasks into spiking versions leads to performance degradation and non-convergence. To address this challenge, we first identify the modules in the architecture design that lead to the severe reduction in spike firing, make targeted improvements, and propose Spike2Former architecture. Second, we propose normalized integer spiking neurons to solve the training stability problem of SNNs with complex architectures. We set a new state-of-the-art for SNNs in various semantic segmentation datasets, with a significant improvement of +12.7% mIoU and 5.0x efficiency on ADE20K, +14.3% mIoU and 5.2x efficiency on VOC2012, and +9.1% mIoU and 6.6x efficiency on CityScapes.

Zitieren

APA

Lei, Z., Yao, M., Hu, J., Luo, X., Lu, Y., Xu, B., & Li, G. (2025). Spike2Former: Efficient Spiking Transformer for High-performance Image Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 39(2), 1364-1372. https://doi.org/10.1609/aaai.v39i2.32126

Vancouver

Lei Z, Yao M, Hu J, Luo X, Lu Y, Xu B, et al. Spike2Former: Efficient Spiking Transformer for High-performance Image Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(2):1364-1372. doi:10.1609/aaai.v39i2.32126

BibTeX
@article{Lei2025,
  author = {Lei, Zhenxin and Yao, Man and Hu, Jiakui and Luo, Xinhao and Lu, Yanye and Xu, Bo and Li, Guoqi},
  title = {Spike2Former: Efficient Spiking Transformer for High-performance Image Segmentation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {2},
  pages = {1364--1372},
  doi = {10.1609/aaai.v39i2.32126}
}
Kostenlos starten →