Brain-inspired spiking neural networks (SNNs) have recently drawn more and
more attention due to their event-driven and energy-efficient characteristics.
The integration of storage and computation paradigm on neuromorphic hardwares
makes SNNs much different from Deep Neural Networks (DNNs). In this paper, we
argue that SNNs may not benefit from the weight-sharing mechanism, which can
effectively reduce parameters and improve inference efficiency in DNNs, in some
hardwares, and assume that an SNN with unshared convolution kernels could
perform better. Motivated by this assumption, a training-inference decoupling
method for SNNs named as Real Spike is proposed, which not only enjoys both
unshared convolution kernels and binary spikes in inference-time but also
maintains both shared convolution kernels and Real-valued Spikes during
training. This decoupling mechanism of SNN is realized by a re-parameterization
technique. Furthermore, based on the training-inference-decoupled idea, a
series of different forms for implementing Real Spike on different levels are
presented, which also enjoy shared convolutions in the inference and are
friendly to both neuromorphic and non-neuromorphic hardware platforms. A
theoretical proof is given to clarify that the Real Spike-based SNN network is
superior to its vanilla counterpart. Experimental results show that all
different Real Spike versions can consistently improve the SNN performance.
Moreover, the proposed method outperforms the state-of-the-art models on both
non-spiking static and neuromorphic datasets.

本文提出了一种用于 SNNs 的训练 - 推理分离方法 ——Real Spike，该方法不仅享有未共享的卷积核和二进制脉冲推理时间，而且在训练期间还保持了共享卷积核和实值脉冲。通过参数重新调整技术，实现了 SNN 的这种解耦机制。此外，本文还提出了几种不同形式的 Real Spike，适用于不同的硬件平台，并在多个数据集上表现出比现有模型更好的性能。