arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.14744cs.NEcs.CVcs.LG
收藏

FSTA-SNN:用于脉冲神经网络的基于频率的时空注意力模块

FSTA-SNN:Frequency-based Spatial-Temporal Attention Module for Spiking Neural Networks

Zhejiang University-University of Illinois Urbana Champaign Institute(浙江大学-伊利诺伊大学厄巴纳-香槟分校研究院);The College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);School of Computer Science and Technology, Dalian University of Technology(大连理工大学计算机科学与技术学院)

Kairong Yu, Tianqing Zhang, Hongwei Wang, Qi Xu

AI总结:

本文分析SNN时空脉冲特性,提出基于频率的时空注意力模块FSTA以抑制冗余脉冲特征,在多个数据集上显著降低脉冲发放率并提升性能。

摘要:

脉冲神经网络(SNNs)因其固有的能量效率,正逐渐成为人工神经网络(ANNs)的一种有前景的替代方案。由于SNNs中脉冲生成固有的稀疏性,对中间输出脉冲的深入分析和优化往往被忽视。这种忽视显著限制了SNNs固有的能量效率,并削弱了其在时空特征提取方面的优势,导致精度不足和不必要的能量消耗。在本工作中,我们从时间和空间两个角度分析了SNNs固有的脉冲特性。在空间分析方面,我们发现浅层倾向于学习特征的垂直变化,而深层则逐渐学习特征的水平变化。在时间分析方面,我们观察到不同时间步之间的特征学习没有显著差异。这表明增加时间步对特征学习的影响有限。基于这些分析得出的见解,我们提出了一个基于频率的时空注意力(FSTA)模块,以增强SNNs中的特征学习。该模块旨在通过抑制冗余脉冲特征来提高特征学习能力。实验结果表明,引入FSTA模块显著降低了SNNs的脉冲发放率,并在多个数据集上表现出优于最先进基线的性能。

英文摘要:

Spiking Neural Networks (SNNs) are emerging as a promising alternative to Artificial Neural Networks (ANNs) due to their inherent energy efficiency. Owing to the inherent sparsity in spike generation within SNNs, the in-depth analysis and optimization of intermediate output spikes are often neglected. This oversight significantly restricts the inherent energy efficiency of SNNs and diminishes their advantages in spatiotemporal feature extraction, resulting in a lack of accuracy and unnecessary energy expenditure. In this work, we analyze the inherent spiking characteristics of SNNs from both temporal and spatial perspectives. In terms of spatial analysis, we find that shallow layers tend to focus on learning vertical variations, while deeper layers gradually learn horizontal variations of features. Regarding temporal analysis, we observe that there is not a significant difference in feature learning across different time steps. This suggests that increasing the time steps has limited effect on feature learning. Based on the insights derived from these analyses, we propose a Frequency-based Spatial-Temporal Attention (FSTA) module to enhance feature learning in SNNs. This module aims to improve the feature learning capabilities by suppressing redundant spike features.The experimental results indicate that the introduction of the FSTA module significantly reduces the spike firing rate of SNNs, demonstrating superior performance compared to state-of-the-art baselines across multiple datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑