# Spiking-GAN: A Spiking Generative Adversarial Network Using Time-To-First-Spike Coding

arXiv: https://arxiv.org/abs/2106.15420 · HTML: https://mlsanity.com/paper/2106.15420/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 26 references that are in the map.
- First posted on arXiv 29 Jun 2021.

## Builds on (most cited first, 14 of 14)

- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Generative Adversarial Text to Image Synthesis](https://mlsanity.com/paper/1605.05396/) (2016)
- [Deep Learning in Spiking Neural Networks](https://mlsanity.com/paper/1804.08150/) (2018)
- [Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection](https://mlsanity.com/paper/1903.06530/) (2019)
- [S4NN: temporal backpropagation for spiking neural networks with one spike per neuron](https://mlsanity.com/paper/1910.09495/) (2019)
- [T2FSNN: Deep Spiking Neural Networks with Time-to-first-spike Coding](https://mlsanity.com/paper/2003.11741/) (2020)
- [A Survey of Methods for Low-Power Deep Learning and Computer Vision](https://mlsanity.com/paper/2003.11066/) (2020)
- [Unifying Activation- and Timing-based Learning Rules for Spiking Neural Networks](https://mlsanity.com/paper/2006.02642/) (2020)
- [Biologically plausible deep learning -- but how far can we go with shallow networks?](https://mlsanity.com/paper/1905.04101/) (2019)
- [BP-STDP: Approximating Backpropagation using Spike Timing Dependent Plasticity](https://mlsanity.com/paper/1711.04214/) (2017)
- [Low-Power Neuromorphic Hardware for Signal Processing Applications](https://mlsanity.com/paper/1901.03690/) (2019)
- [Generative Adversarial Models for People Attribute Recognition in Surveillance](https://mlsanity.com/paper/1707.02240/) (2017)

## Built on by (most cited first, 8 of 8)

- [Fully Spiking Variational Autoencoder](https://mlsanity.com/paper/2110.00375/) (2021)
- [Spiking Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2306.17046/) (2023)
- [Spiking Generative Adversarial Networks With a Neural Network Discriminator: Local Training, Bayesian Models, and Continual Meta-Learning](https://mlsanity.com/paper/2111.01750/) (2021)
- [Spiking-Diffusion: Vector Quantized Discrete Diffusion Model with Spiking Neural Networks](https://mlsanity.com/paper/2308.10187/) (2023)
- [SDiT: Spiking Diffusion Model with Transformer](https://mlsanity.com/paper/2402.11588/) (2024)
- [Spiking Diffusion Models](https://mlsanity.com/paper/2408.16467/) (2024)
- [Negative Binomial Variational Autoencoders for Overdispersed Latent Modeling](https://mlsanity.com/paper/2508.05423/) (2025)
- [Biologically Inspired Spiking Diffusion Model with Adaptive Lateral Selection Mechanism](https://mlsanity.com/paper/2503.23767/) (2025)

## Abstract (arXiv)

Spiking Neural Networks (SNNs) have shown great potential in solving deep learning problems in an energy-efficient manner. However, they are still limited to simple classification tasks. In this paper, we propose Spiking-GAN, the first spike-based Generative Adversarial Network (GAN). It employs a kind of temporal coding scheme called time-to-first-spike coding. We train it using approximate backpropagation in the temporal domain. We use simple integrate-and-fire (IF) neurons with very high refractory period for our network which ensures a maximum of one spike per neuron. This makes the model much sparser than a spike rate-based system. Our modified temporal loss function called 'Aggressive TTFS' improves the inference time of the network by over 33% and reduces the number of spikes in the network by more than 11% compared to previous works. Our experiments show that on training the network on the MNIST dataset using this approach, we can generate high quality samples. Thereby demonstrating the potential of this framework for solving such problems in the spiking domain.