提出时间移位模块，让脉冲神经网络更高效地利用时间信息
TS-SNN: Temporal Shift Module for Spiking Neural Networks
- 用简单移位操作融合前后时刻的脉冲特征
- 在减少时间步数的情况下达到96.72%准确率
- 轻量设计适合部署在低功耗设备上
脉冲神经网络（SNN）因其生物合理性与低功耗特性，成为类脑计算中的有力候选。尽管其天然具备处理时序信息的能力，但如何平衡时序特征利用与能耗仍是挑战。本文提出针对SNN的时间移位模块（TS-SNN），通过一个新颖的时序移位（TS）模块，在单个时间步内融合过去、当前与未来脉冲特征，采用残差连接避免信息丢失。该模块仅引入一个可学习参数，计算开销极小，可无缝嵌入现有架构。在CIFAR-10（96.72%）、CIFAR-100（80.28%）和ImageNet（70.61%）等基准上实现最优性能，且使用更少时间步，同时保持低能耗。这项工作推动了高效高精度SNN架构的发展。
原文摘要 · Abstract (English)
Spiking Neural Networks (SNNs) are increasingly recognized for their biological plausibility and energy efficiency, positioning them as strong alternatives to Artificial Neural Networks (ANNs) in neuromorphic computing applications. SNNs inherently process temporal information by leveraging the precise timing of spikes, but balancing temporal feature utilization with low energy consumption remains a challenge. In this work, we introduce Temporal Shift module for Spiking Neural Networks (TS-SNN), which incorporates a novel Temporal Shift (TS) module to integrate past, present, and future spike features within a single timestep via a simple yet effective shift operation. A residual combination method prevents information loss by integrating shifted and original features. The TS module is lightweight, requiring only one additional learnable parameter, and can be seamlessly integrated into existing architectures with minimal additional computational cost. TS-SNN achieves state-of-the-art performance on benchmarks like CIFAR-10 (96.72\%), CIFAR-100 (80.28\%), and ImageNet (70.61\%) with fewer timesteps, while maintaining low energy consumption. This work marks a significant step forward in developing efficient and accurate SNN architectures.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。