Papers › Spiking-Diffusion: Vector Quantized Discrete Diffusion Model with Spiking Neural Networks

Spiking-Diffusion: Vector Quantized Discrete Diffusion Model with Spiking Neural Networks

20 Aug 2023arXiv:2308.10187archive 2025-07-28

Mingxuan Liu, Jie Gan, Rui Wen, Tao Li, Yongli Chen, Hong Chen

Spiking neural networks (SNNs) have tremendous potential for energy-efficient neuromorphic chips due to their binary and event-driven architecture. SNNs have been primarily used in classification tasks, but limited exploration on image generation tasks. To fill the gap, we propose a Spiking-Diffusion model, which is based on the vector quantized discrete diffusion model. First, we develop a vector quantized variational autoencoder with SNNs (VQ-SVAE) to learn a discrete latent space for images. In VQ-SVAE, image features are encoded using both the spike firing rate and postsynaptic potential, and an adaptive spike generator is designed to restore embedding features in the form of spike trains. Next, we perform absorbing state diffusion in the discrete latent space and construct a spiking diffusion image decoder (SDID) with SNNs to denoise the image. Our work is the first to build the diffusion model entirely from SNN layers. Experimental results on MNIST, FMNIST, KMNIST, Letters, and Cifar10 demonstrate that Spiking-Diffusion outperforms the existing SNN-based generation model. We achieve FIDs of 37.50, 91.98, 59.23, 67.41, and 120.5 on the above datasets respectively, with reductions of 58.60\%, 18.75\%, 64.51\%, 29.75\%, and 44.88\% in FIDs compared with the state-of-art work. Our code will be available at \url{https://github.com/Arktis2022/Spiking-Diffusion}.

PaperPDFCode

Code

Arktis2022/Spiking-Diffusion officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderImage Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation EMNIST-Letters Spiking-Diffusion FID 67.41 #1 of 1 Archive leaderboard report
Image Generation Fashion-MNIST Spiking-Diffusion FID 91.98 #7 of 7 Archive leaderboard report
Image Generation KMNIST Spiking-Diffusion FID 59.23 #1 of 1 Archive leaderboard report
Image Generation MNIST Spiking-Diffusion FID 27.61 #12 of 15 Archive leaderboard report
Image Generation MNIST Spiking-Diffusion Precision 0.83 #12 of 15 Archive leaderboard report
Image Generation MNIST Spiking-Diffusion Recall 0.65 #12 of 15 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

DiffusionSNN

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections