Spiking Denoising Diffusion Probabilistic Models

TL;DR

This paper introduces Spiking Denoising Diffusion Probabilistic Models (SDDPM), a novel SNN-based generative model that achieves high-quality samples with significantly reduced energy consumption and state-of-the-art performance on standard datasets.

Contribution

The paper presents a new SNN-based generative model, SDDPM, with a purely Spiking U-Net architecture and a threshold-guided strategy, advancing energy-efficient generative modeling.

Findings

Achieves state-of-the-art results on CIFAR-10 and CelebA datasets.

Uses only 4 time steps, greatly reducing energy consumption.

Outperforms other SNN-based generative models by up to 12x and 6x.

Abstract

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 12x and 6x improvement on the CIFAR-10 and the CelebA datasets, respectively. Moreover, we propose a threshold-guided strategy that can further improve the performances by 2.69% 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. Our code is available at https://github.com/AndyCao1125/SDDPM.