App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 4

Spatial-frequency token mixer with spiking dilated separable attention and frequency learning

Tao Huixing
Chen Yunhua
Chen Pinghua
Liao Zhaohui
Zhou Honghong
School of Computer Science and Technology, Guangdong University of Technology, Guangzhou 510640, China
DOI: 10.19734/j.issn.1001-3695.2025.08.0303

Abstract

Spiking transformers have injected new vitality into spiking neural network (SNN) research due to their potential for energy efficiency and superior performance. However, they still suffer from quadratic computational complexity and unsatisfactory performance. To address these issues, this paper proposed a spatial-frequency token mixer (SFTM) that integrates two branches: a spiking dilated separable attention (SDSA) mechanism and a Fourier transform-based frequency learner (FTFL) . The SDSA module employed large-kernel depthwise convolutions to model long-range dependencies with linear complexity, substantially reducing computational overhead. The FTFL module restored high-frequency details through spectral transformation and adaptive weighting, effectively countering the low-pass filtering characteristics of spiking attention mechanisms. Additionally, the paper designed a spiking depth-wise feed-forward network (SDWFFN) to facilitate cross-channel information exchange. Experiments on CIFAR-10/100 and multiple neuromorphic datasets demonstrate that the proposed SFformer achieved comparable or superior accuracy to state-of-the-art models. Specifically, the model achieved 81.34% accuracy on CIFAR-100, outperforming the previous best result by 3.13%, with an energy consumption of only 0.27mJ, validating its significant energy efficiency while maintaining high performance.

Foundation Support

广东省重点领域研发计划项目(2023B1111050010)
广东省自然科学基金资助项目(2025A1515012243)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.08.0303
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 4

Publish History

[2025-12-18] Accepted Paper

Cite This Article

陶慧杏, 陈云华, 陈平华, 等. 基于脉冲膨胀可分离注意力与频域学习的双域令牌混合器 [J]. 计算机应用研究, 2026, 43 (4). (2025-12-19). https://doi.org/10.19734/j.issn.1001-3695.2025.08.0303. (Tao Huixing, Chen Yunhua, Chen Pinghua, et al. Spatial-frequency token mixer with spiking dilated separable attention and frequency learning [J]. Application Research of Computers, 2026, 43 (4). (2025-12-19). https://doi.org/10.19734/j.issn.1001-3695.2025.08.0303. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)