SpikeZIP-TF: Conversion is All You Need for Transformer-based SNN

Kang You, Zekai Xu, Chen Nie, Zhijie Deng, Qinghai Guo +2 more
2/12/2026

No official code found. Best implementation: Intelligent-Computing-Research-Group/SpikeZIP-TF (51 stars, last commit 2024-12-04).

Abstract

Spiking neural network (SNN) has attracted great attention due to its characteristic of high efficiency and accuracy. Currently, the ANN-to-SNN conversion methods can obtain ANN on-par accuracy SNN with ultra-low latency (8 time-steps) in CNN structure on computer vision (CV) tasks. However, as Transformer-based networks have achieved prevailing precision on both CV and natural language processing (NLP), the Transformer-based SNNs are still encounting the lower accuracy w.r.t the ANN counterparts. In this work, we introduce a novel ANN-to-SNN conversion method called SpikeZIP-TF, where ANN and SNN are exactly equivalent, thus incurring no accuracy degradation. SpikeZIP-TF achieves 83.82% accuracy on CV dataset (ImageNet) and 93.79% accuracy on NLP dataset (SST-2), which are higher than SOTA Transformer-based SNNs. The code is available in GitHub: https://github.com/Intelligent-Computing-Research-Group/SpikeZIP_transformer

View on arXivView PDF

Code Implementations(1)

Intelligent-Computing-Research-Group/SpikeZIP-TFCommunity100%

Official repository of SpikeZIP-TF in ICML2024

5115Shell, PythonMay 30, 20241 years ago

Similar Papers

Towards High-performance Spiking Transformers from ANN to SNN Conversion

85% match1 repo192025

The Progression of Transformers from Language to Vision to MOT: A Literature Review on Multi-Object Tracking with Transformers

83% match2024

FastHDRNet: A new efficient method for SDR-to-HDR Translation

82% match2024

Mechanisms of Generative Image-to-Image Translation Networks

82% match2024

KANICE: Kolmogorov-Arnold Networks with Interactive Convolutional Elements

81% match2 repos32024

GCV-Turbo: End-to-end Acceleration of GNN-based Computer Vision Tasks on FPGA

81% match2024

Cite this paper

@article{you2026spikeziptf,
  title  = {SpikeZIP-TF: Conversion is All You Need for Transformer-based SNN},
  author = {Kang You and Zekai Xu and Chen Nie and Zhijie Deng and Qinghai Guo and Xiang Wang and Zhezhi He},
  year   = {2026},
  eprint = {2406.03470},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2406.03470},
  journal = {ICML 2024 2024}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.03470.svg)](https://codeofpaper.com/paper/2406.03470)

Discussion