FSTA-SNN:Frequency-based Spatial-Temporal Attention Module for Spiking Neural Networks
This work addresses energy efficiency and accuracy issues in SNNs, which are critical for low-power AI applications, though it appears incremental as it builds on existing SNN optimization methods.
The paper tackled the problem of inefficient spike generation in Spiking Neural Networks (SNNs) by analyzing spiking characteristics and proposing a Frequency-based Spatial-Temporal Attention (FSTA) module, which significantly reduced spike firing rates and outperformed state-of-the-art baselines on multiple datasets.
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.