# QGAN: Quantized Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1901.08263 · HTML: https://mlsanity.com/paper/1901.08263/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jan 2019.

## Built on by (most cited first, 20 of 20)

- [GANs Can Play Lottery Tickets Too](https://mlsanity.com/paper/2106.00134/) (2021)
- [Fast and Memory-Efficient Video Diffusion Using Streamlined Inference](https://mlsanity.com/paper/2411.01171/) (2024)
- [A Quantum Generative Adversarial Network for distributions](https://mlsanity.com/paper/2110.02742/) (2021)
- [Training Deep Neural Networks with Joint Quantization and Pruning of Weights and Activations](https://mlsanity.com/paper/2110.08271/) (2021)
- [Don't Be So Dense: Sparse-to-Sparse GAN Training Without Sacrificing Performance](https://mlsanity.com/paper/2203.02770/) (2022)
- [Cut Inner Layers: A Structured Pruning Strategy for Efficient U-Net GANs](https://mlsanity.com/paper/2206.14658/) (2022)
- [Quantization of Generative Adversarial Networks for Efficient Inference: a Methodological Study](https://mlsanity.com/paper/2108.13996/) (2021)
- [Discriminator-Cooperated Feature Map Distillation for GAN Compression](https://mlsanity.com/paper/2212.14169/) (2022)
- [Quantum Deep Learning for Mutant COVID-19 Strain Prediction](https://mlsanity.com/paper/2203.03556/) (2022)
- [CoroNetGAN: Controlled Pruning of GANs via Hypernetworks](https://mlsanity.com/paper/2403.08261/) (2024)
- [Evaluating Post-Training Compression in GANs using Locality-Sensitive Hashing](https://mlsanity.com/paper/2103.11912/) (2021)
- [Fingerprinting Image-to-Image Generative Adversarial Networks](https://mlsanity.com/paper/2106.11760/) (2021)
- [Exploring Content Relationships for Distilling Efficient GANs](https://mlsanity.com/paper/2212.11091/) (2022)
- [E2GAN: Efficient Training of Efficient GANs for Image-to-Image Translation](https://mlsanity.com/paper/2401.06127/) (2024)
- [Leveraging Modified Ex Situ Tomography Data for Segmentation of In Situ Synchrotron X-Ray Computed Tomography](https://mlsanity.com/paper/2504.19200/) (2025)
- [Quantized Proximal Averaging Network for Analysis Sparse Coding](https://mlsanity.com/paper/2105.06211/) (2021)
- [A Survey on GAN Acceleration Using Memory Compression Technique](https://mlsanity.com/paper/2108.06626/) (2021)
- [DGL-GAN: Discriminator Guided Learning for GAN Compression](https://mlsanity.com/paper/2112.06502/) (2021)
- [A Unified Compression Framework for Efficient Speech-Driven Talking-Face Generation](https://mlsanity.com/paper/2304.00471/) (2023)
- [Low-Bit, High-Fidelity: Optimal Transport Quantization for Flow Matching](https://mlsanity.com/paper/2511.11418/) (2025)

## Abstract (arXiv)

The intensive computation and memory requirements of generative adversarial neural networks (GANs) hinder its real-world deployment on edge devices such as smartphones. Despite the success in model reduction of CNNs, neural network quantization methods have not yet been studied on GANs, which are mainly faced with the issues of both the effectiveness of quantization algorithms and the instability of training GAN models. In this paper, we start with an extensive study on applying existing successful methods to quantize GANs. Our observation reveals that none of them generates samples with reasonable quality because of the underrepresentation of quantized values in model weights, and the generator and discriminator networks show different sensitivities upon quantization methods. Motivated by these observations, we develop a novel quantization method for GANs based on EM algorithms, named as QGAN. We also propose a multi-precision algorithm to help find the optimal number of bits of quantized GAN models in conjunction with corresponding result qualities. Experiments on CIFAR-10 and CelebA show that QGAN can quantize GANs to even 1-bit or 2-bit representations with results of quality comparable to original models.