paper-with-me

홈 › Papers

STEP: A Unified Spiking Transformer Evaluation Platform for Fair and Reproducible Benchmarking

2025-05-16 · Sicheng Shen, Dongcheng Zhao, Linghao Feng, Zeyang Yue, Jindong Li, Tenglong Li, Guobin Shen, Yi Zeng

Spiking Transformers have recently emerged as promising architectures for combining the efficiency of spiking neural networks with the representational power of self-attention. However, the lack of standardized implementations, evaluation pipelines, and consistent design choices has hindered fair comparison and principled analysis. In this paper, we introduce \textbf{STEP}, a unified benchmark framework for Spiking Transformers that supports a wide range of tasks, including classification, segmentation, and detection across static, event-based, and sequential datasets. STEP provides modular support for diverse components such as spiking neurons, input encodings, surrogate gradients, and multiple backends (e.g., SpikingJelly, BrainCog). Using STEP, we reproduce and evaluate several representative models, and conduct systematic ablation studies on attention design, neuron types, encoding schemes, and temporal modeling capabilities. We also propose a unified analytical model for energy estimation, accounting for spike sparsity, bitwidth, and memory access, and show that quantized ANNs may offer comparable or better energy efficiency. Our results suggest that current Spiking Transformers rely heavily on convolutional frontends and lack strong temporal modeling, underscoring the need for spike-native architectural innovations. The full code is available at: https://github.com/Fancyssc/STEP

📄 PDF Abstract BibTeX arXiv:2505.11151

Code (1)

fancyssc/step 공식 구현 pytorch

Tasks

Benchmarking

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

STAS: Spatio-Temporal Adaptive Computation Time for Spiking Transformers

2025-08-19 · Donghwa Kang, Doohyun Kim, Sang-Ki Ko, Jinkyu Lee 외 arxiv

Spiking neural networks (SNNs) offer energy efficiency over artificial neural networks (ANNs) but suffer from high latency and computational overhead due to their multi-timestep operational nature. While various dynamic …

Stochastic Spiking Attention: Accelerating Attention with Stochastic Computing in Spiking Networks

2024-02-14 · Zihang Song, Prabodh Katti, Osvaldo Simeone, Bipin Rajendran

Spiking Neural Networks (SNNs) have been recently integrated into Transformer architectures due to their potential to reduce computational demands and to improve power efficiency. Yet, the implementation of the attention…

GPU

SpiLiFormer: Enhancing Spiking Transformers with Lateral Inhibition

2025-03-20 · Zeqi Zheng, Yanchen Huang, Yingchao Yu, Zizheng Zhu 외

Spiking Neural Networks (SNNs) based on Transformers have garnered significant attention due to their superior performance and high energy efficiency. However, the spiking attention modules of most existing Transformer-b…

ViT-LCA: A Neuromorphic Approach for Vision Transformers

2024-10-31 · Sanaz Mahmoodi Takaghaj

The recent success of Vision Transformers has generated significant interest in attention mechanisms and transformer architectures. Although existing methods have proposed spiking self-attention mechanisms compatible wit…

DS2TA: Denoising Spiking Transformer with Attenuated Spatiotemporal Attention

2024-09-20 · Boxun Xu, Hejia Geng, Yuxuan Yin, Peng Li

Vision Transformers (ViT) are current high-performance models of choice for various vision applications. Recent developments have given rise to biologically inspired spiking transformers that thrive in ultra-low power op…

Denoising