SDiT: Spiking Diffusion Model with Transformer

arXiv:2402.11588v1 Announce Type: new
Abstract: Spiking neural networks (SNNs) have low power consumption and bio-interpretable characteristics, and are considered to have tremendous potential for energy-efficient computing. However, the exploration of SNNs on image generation tasks remains very limited, and a unified and effective structure for SNN-based generative models has yet to be proposed. In this paper, we explore a novel diffusion model architecture within spiking neural networks. We utilize transformer to replace the commonly used U-net structure in mainstream diffusion …

abstract arxiv bio computing consumption cs.ai cs.cv diffusion diffusion model energy exploration generative generative models image image generation low low power networks neural networks power power consumption snn spiking neural networks tasks transformer type