Spiking neural networks (SNNs) have ultra-low energy consumption and high
biological plausibility due to their binary and bio-driven nature compared with
artificial neural networks (ANNs). While previous research has primarily
focused on enhancing the performance of SNNs in classification tasks, the
generative potential of SNNs remains relatively unexplored. In our paper, we
put forward Spiking Denoising Diffusion Probabilistic Models (SDDPM), a new
class of SNN-based generative models that achieve high sample quality. To fully
exploit the energy efficiency of SNNs, we propose a purely Spiking U-Net
architecture, which achieves comparable performance to its ANN counterpart
using only 4 time steps, resulting in significantly reduced energy consumption.
Extensive experimental results reveal that our approach achieves
state-of-the-art on the generative tasks and substantially outperforms other
SNN-based generative models, achieving up to $12\times$ and $6\times$
improvement on the CIFAR-10 and the CelebA datasets, respectively. Moreover, we
propose a threshold-guided strategy that can further improve the performances
by 16.7% in a training-free manner. The SDDPM symbolizes a significant
advancement in the field of SNN generation, injecting new perspectives and
potential avenues of exploration.

本文提出了一种新的基于脉冲神经网络的生成模型 ——SDDPM，通过仅使用 4 个时间步骤的纯脉冲 U-Net 体系结构，实现与其 ANN 模型的可比性能，从而充分利用脉冲神经网络的能源效率，并在 CIFAR-10 和 CelebA 数据集上实现了卓越的性能，是脉冲神经网络生成领域的重大进展。