# Quantization of Generative Adversarial Networks for Efficient Inference: a Methodological Study

arXiv: https://arxiv.org/abs/2108.13996 · HTML: https://mlsanity.com/paper/2108.13996/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 33 references that are in the map.
- First posted on arXiv 31 Aug 2021.

## Builds on (most cited first, 26 of 26)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [Channel Pruning for Accelerating Very Deep Neural Networks](https://mlsanity.com/paper/1707.06168/) (2017)
- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [Up or Down? Adaptive Rounding for Post-Training Quantization](https://mlsanity.com/paper/2004.10568/) (2020)
- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction](https://mlsanity.com/paper/2102.05426/) (2021)
- [Data-Free Quantization Through Weight Equalization and Bias Correction](https://mlsanity.com/paper/1906.04721/) (2019)
- [LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks](https://mlsanity.com/paper/1807.10029/) (2018)
- [Variational Dropout Sparsifies Deep Neural Networks](https://mlsanity.com/paper/1701.05369/) (2017)
- [Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming](https://mlsanity.com/paper/2006.10518/) (2020)
- [Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks](https://mlsanity.com/paper/1903.08066/) (2019)
- [HAWQV3: Dyadic Neural Network Quantization](https://mlsanity.com/paper/2011.10680/) (2020)
- [Value-aware Quantization for Training and Inference of Neural Networks](https://mlsanity.com/paper/1804.07802/) (2018)
- [GAN Slimming: All-in-One GAN Compression by A Unified Optimization Framework](https://mlsanity.com/paper/2008.11062/) (2020)
- [QGAN: Quantized Generative Adversarial Networks](https://mlsanity.com/paper/1901.08263/) (2019)

## Built on by (most cited first, 4 of 4)

- [Cut Inner Layers: A Structured Pruning Strategy for Efficient U-Net GANs](https://mlsanity.com/paper/2206.14658/) (2022)
- [Accelerating Inference of Discrete Autoregressive Normalizing Flows by Selective Jacobi Decoding](https://mlsanity.com/paper/2505.24791/) (2025)
- [A Unified Compression Framework for Efficient Speech-Driven Talking-Face Generation](https://mlsanity.com/paper/2304.00471/) (2023)
- [SafeCiM: Investigating Resilience of Hybrid Floating-Point Compute-in-Memory Deep Learning Accelerators](https://mlsanity.com/paper/2512.00059/) (2025)

## Abstract (arXiv)

Generative adversarial networks (GANs) have an enormous potential impact on digital content creation, e.g., photo-realistic digital avatars, semantic content editing, and quality enhancement of speech and images. However, the performance of modern GANs comes together with massive amounts of computations performed during the inference and high energy consumption. That complicates, or even makes impossible, their deployment on edge devices. The problem can be reduced with quantization -- a neural network compression technique that facilitates hardware-friendly inference by replacing floating-point computations with low-bit integer ones. While quantization is well established for discriminative models, the performance of modern quantization techniques in application to GANs remains unclear. GANs generate content of a more complex structure than discriminative models, and thus quantization of GANs is significantly more challenging. To tackle this problem, we perform an extensive experimental study of state-of-art quantization techniques on three diverse GAN architectures, namely StyleGAN, Self-Attention GAN, and CycleGAN. As a result, we discovered practical recipes that allowed us to successfully quantize these models for inference with 4/8-bit weights and 8-bit activations while preserving the quality of the original full-precision models.