# CSDformer: A Conversion Method for Fully Spike-Driven Transformer

arXiv: https://arxiv.org/abs/2509.17461 · HTML: https://mlsanity.com/paper/2509.17461/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 46 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [Deep Residual Learning in Spiking Neural Networks](https://mlsanity.com/paper/2102.04159/) (2021)
- [Going Deeper With Directly-Trained Larger Spiking Neural Networks](https://mlsanity.com/paper/2011.05280/) (2020)
- [Spikformer: When Spiking Neural Network Meets Transformer](https://mlsanity.com/paper/2209.15425/) (2022)
- [Going Deeper in Spiking Neural Networks: VGG and Residual Architectures](https://mlsanity.com/paper/1802.02627/) (2018)
- [Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting](https://mlsanity.com/paper/2202.11946/) (2022)
- [Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection](https://mlsanity.com/paper/1903.06530/) (2019)
- [SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence](https://mlsanity.com/paper/2310.16620/) (2023)
- [Spike-driven Transformer](https://mlsanity.com/paper/2307.01694/) (2023)
- [Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networks](https://mlsanity.com/paper/2103.00476/) (2021)
- [Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks](https://mlsanity.com/paper/2303.04347/) (2023)
- [Advancing Spiking Neural Networks towards Deep Residual Learning](https://mlsanity.com/paper/2112.08954/) (2021)
- [Deep Directly-Trained Spiking Neural Networks for Object Detection](https://mlsanity.com/paper/2307.11411/) (2023)
- [Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANN](https://mlsanity.com/paper/2305.19868/) (2023)
- [Comparing SNNs and RNNs on Neuromorphic Vision Datasets: Similarities and Differences](https://mlsanity.com/paper/2005.02183/) (2020)
- [Reducing ANN-SNN Conversion Error through Residual Membrane Potential](https://mlsanity.com/paper/2302.02091/) (2023)
- [Bridging the Gap between ANNs and SNNs by Calibrating Offset Spikes](https://mlsanity.com/paper/2302.10685/) (2023)
- [Masked Spiking Transformer](https://mlsanity.com/paper/2210.01208/) (2022)
- [Rapid online learning and robust recall in a neuromorphic olfactory circuit](https://mlsanity.com/paper/1906.07067/) (2019)
- [SpikeZIP-TF: Conversion is All You Need for Transformer-based SNN](https://mlsanity.com/paper/2406.03470/) (2024)
- [Towards Lossless ANN-SNN Conversion under Ultra-Low Latency with Dual-Phase Optimization](https://mlsanity.com/paper/2205.07473/) (2022)

## Abstract (arXiv)

Spike-based transformer is a novel architecture aiming to enhance the performance of spiking neural networks while mitigating the energy overhead inherent to transformers. However, methods for generating these models suffer from critical limitations: excessive training costs introduced by direct training methods, or unavoidably hardware-unfriendly operations in existing conversion methods. In this paper, we propose CSDformer, a novel conversion method for fully spike-driven transformers. We tailor a conversion-oriented transformer-based architecture and propose a new function NReLU to replace softmax in self-attention. Subsequently, this model is quantized and trained, and converted into a fully spike-driven model with temporal decomposition technique. Also, we propose delayed Integrate-andFire neurons to reduce conversion errors and improve the performance of spiking models. We evaluate CSDformer on ImageNet, CIFAR-10 and CIFAR-100 datasets and achieve 76.36% top-1 accuracy under 7 time-steps on ImageNet, demonstrating superiority over state-of-the-art models. Furthermore, CSDformer eliminates the need for training SNNs, thereby reducing training costs (reducing computational resource by 75% and accelerating training speed by 2-3×). To the best of our knowledge, this is the first fully spike-driven transformer-based model developed via conversion method, achieving high performance under ultra-low latency, while dramatically reducing both computational complexity and training overhead.