Fully Spiking Denoising Diffusion Implicit Models
This work addresses the energy and time inefficiencies of diffusion models for applications requiring fast, low-power generative AI, though it is incremental as it adapts existing diffusion methods to SNNs.
The authors tackled the problem of high computational cost and long inference times in diffusion models by proposing a fully spiking denoising diffusion implicit model (FSDDIM) that leverages spiking neural networks (SNNs) for energy-efficient generation, demonstrating that it outperforms the state-of-the-art fully spiking generative model.
Spiking neural networks (SNNs) have garnered considerable attention owing to their ability to run on neuromorphic devices with super-high speeds and remarkable energy efficiencies. SNNs can be used in conventional neural network-based time- and energy-consuming applications. However, research on generative models within SNNs remains limited, despite their advantages. In particular, diffusion models are a powerful class of generative models, whose image generation quality surpass that of the other generative models, such as GANs. However, diffusion models are characterized by high computational costs and long inference times owing to their iterative denoising feature. Therefore, we propose a novel approach fully spiking denoising diffusion implicit model (FSDDIM) to construct a diffusion model within SNNs and leverage the high speed and low energy consumption features of SNNs via synaptic current learning (SCL). SCL fills the gap in that diffusion models use a neural network to estimate real-valued parameters of a predefined probabilistic distribution, whereas SNNs output binary spike trains. The SCL enables us to complete the entire generative process of diffusion models exclusively using SNNs. We demonstrate that the proposed method outperforms the state-of-the-art fully spiking generative model.