mlsanityData to 7 Oct 2026

Fully Spiking Variational Autoencoder

arXiv 2110.00375 ↗First posted 26 Sep 2021cs.NE cs.CV cs.LGcited by 22

Not on the map. Why?

Abstract (arXiv)

Spiking neural networks (SNNs) can be run on neuromorphic devices with ultra-high speed and ultra-low energy consumption because of their binary and event-driven nature. Therefore, SNNs are expected to have various applications, including as generative models being running on edge devices to create high-quality images. In this study, we build a variational autoencoder (VAE) with SNN to enable image generation. VAE is known for its stability among generative models; recently, its quality advanced. In vanilla VAE, the latent space is represented as a normal distribution, and floating-point calculations are required in sampling. However, this is not possible in SNNs because all features must be binary time series data. Therefore, we constructed the latent space with an autoregressive SNN model, and randomly selected samples from its output to sample the latent variables. This allows the latent variables to follow the Bernoulli process and allows variational learning. Thus, we build the Fully Spiking Variational Autoencoder where all modules are constructed with SNN. To the best of our knowledge, we are the first to build a VAE only with SNN layers. We experimented with several datasets, and confirmed that it can generate images with the same or better quality compared to conventional ANNs. The code is available at https://github.com/kamata1729/FullySpikingVAE

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 21 of its 46 references that are in the map. First posted on arXiv 26 Sep 2021.

Builds on

21 of 46 references.

References · 21

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2017Neural Discrete Representation Learningcited by 4,650
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  5. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  6. 2016Improved Techniques for Training GANscited by 2,938
  7. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  8. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 779
  9. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 635
  10. 2015A Recurrent Latent Variable Model for Sequential Datacited by 362
  11. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 268
  12. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 222
9 more
  1. 2017SuperSpike: Supervised learning in multi-layer spiking neural networkscited by 178
  2. 2019Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detectioncited by 174
  3. 2020Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networkscited by 98
  4. 2020Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural Networkscited by 98
  5. 2021On Aliased Resizing and Surprising Subtleties in GAN Evaluationcited by 51
  6. 2021Learning to Time-Decode in Spiking Neural Networks Through the Information Bottleneckcited by 15
  7. 2021Spiking-GAN: A Spiking Generative Adversarial Network Using Time-To-First-Spike Codingcited by 8
  8. 2020Rescuing neural spike train models from bad MLEcited by 6
  9. 2016A New Learning Method for Inference Accuracy, Core Occupation, and Performance Co-optimization on TrueNorth Chipcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 7; 2024: 7; 2025: 5; 2026: 1.

22 papers.

Sort:

By area:

  1. 2022TCJA-SNN: Temporal-Channel Joint Attention for Spiking Neural Networkscited by 33
  2. 2023Spiking Denoising Diffusion Probabilistic Modelscited by 18
  3. 2024Autonomous Driving with Spiking Neural Networkscited by 12
  4. 2024Poisson Variational Autoencodercited by 11
  5. 2023Tensor Decomposition Based Attention Module for Spiking Neural Networkscited by 8
  6. 2023Spiking-Diffusion: Vector Quantized Discrete Diffusion Model with Spiking Neural Networkscited by 7
  7. 2023eVAE: Evolutionary Variational Autoencodercited by 6
  8. 2023Temporal Conditioning Spiking Latent Variable Models of the Neural Response to Natural Visual Scenescited by 4
  9. 2024SDiT: Spiking Diffusion Model with Transformercited by 4
  10. 2025SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and O(T) Complexitycited by 4
  11. 2024Spiking Diffusion Modelscited by 3
  12. 2025EA: An Event Autoencoder for High-Speed Vision Sensingcited by 3
10 more
  1. 2023ESVAE: An Efficient Spiking Variational Autoencoder with Reparameterizable Poisson Spiking Samplingcited by 2
  2. 2023Fully Spiking Denoising Diffusion Implicit Modelscited by 2
  3. 2024Temporal Reversal Regularization for Spiking Neural Networks: Hybrid Spatio-Temporal Invariance for Generalizationcited by 2
  4. 2025Edge Intelligence with Spiking Neural Networkscited by 2
  5. 2025Negative Binomial Variational Autoencoders for Overdispersed Latent Modelingcited by 2
  6. 2022Spiking Variational Graph Auto-Encoders for Efficient Graph Representation Learningcited by 1
  7. 2024Predictive Temporal Attention on Event-based Video Stream for Energy-efficient Situation Awarenesscited by 1
  8. 2024Topology Optimization of Random Memristors for Input-Aware Dynamic SNNcited by 0
  9. 2025Biologically Inspired Spiking Diffusion Model with Adaptive Lateral Selection Mechanismcited by 0
  10. 2026LiteEvent-AE: Lightweight Autoencoder for Event-Based Vision on Low-Latency Energy-Constrained Edge Devicescited by 0