mlsanityData to 7 Oct 2026

MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesis

arXiv 2104.04767 ↗First posted 10 Apr 2021cs.CV eess.IVcited by 10

Not on the map. Why?

Abstract (arXiv)

In recent years, the use of Generative Adversarial Networks (GANs) has become very popular in generative image modeling. While style-based GAN architectures yield state-of-the-art results in high-fidelity image synthesis, computationally, they are highly complex. In our work, we focus on the performance optimization of style-based generative models. We analyze the most computationally hard parts of StyleGAN2, and propose changes in the generator network to make it possible to deploy style-based generative networks in the edge devices. We introduce MobileStyleGAN architecture, which has x3.5 fewer parameters and is x9.5 less computationally complex than StyleGAN2, while providing comparable quality.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 25 of its 35 references that are in the map. First posted on arXiv 10 Apr 2021.

Builds on

25 of 35 references.

References · 25

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  6. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  7. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  8. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  9. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  10. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  11. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  12. 2019Searching for MobileNetV3cited by 1,984
13 more
  1. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  2. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  3. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  4. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  5. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
  6. 2018Multi-level Wavelet-CNN for Image Restorationcited by 184
  7. 2021Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesiscited by 140
  8. 2018SqueezeNext: Hardware-Aware Neural Network Designcited by 61
  9. 2020AutoGAN-Distiller: Searching to Compress Generative Adversarial Networkscited by 50
  10. 2020GAN Slimming: All-in-One GAN Compression by A Unified Optimization Frameworkcited by 44
  11. 2019Compressing GANs using Knowledge Distillationcited by 31
  12. 2017Wavelet Convolutional Neural Networks for Texture Classificationcited by 21
  13. 2020TinyGAN: Distilling BigGAN for Conditional Image Generationcited by 14

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 5; 2023: 1; 2024: 1.

10 papers.

  1. 2022One-Shot Adaptation of GAN in Just One CLIPcited by 31
  2. 2021Styleformer: Transformer based Generative Adversarial Networks with Style Vectorcited by 27
  3. 2022Efficient Image Generation with Variadic Attention Headscited by 17
  4. 2022Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesiscited by 12
  5. 2022Mind the Gap in Distilling StyleGANscited by 10
  6. 2022Video Coding Using Learned Latent GAN Compressioncited by 4
  7. 2024Learning Images Across Scales Using Adversarial Trainingcited by 3
  8. 2021Emojich -- zero-shot emoji generation using Russian language: a technical reportcited by 2
  9. 2021DGL-GAN: Discriminator Guided Learning for GAN Compressioncited by 0
  10. 2023SCPAT-GAN: Structural Constrained and Pathology Aware Convolutional Transformer-GAN for Virtual Histology Staining of Human Coronary OCT imagescited by 0