Skip to content
项目

sheqi/GAN_Review has 443 GitHub stars and 76 forks. GitHot measured 0 stars in 24 hours. Last checked 2026-11-19 16:51 UTC. Last push 2021-08-14.

这些数字如何统计

实测星标增长

24小时
0
7天
正在收集历史
15天
正在收集历史
1个月
正在收集历史

各周期内的星标净变化,周期相互重叠,并非每日新增。缺失的测量保持空白。星标代表关注度,不代表软件质量。

关于

A Survey and Taxonomy of the Recent GANs Development,computer vision & time series

机器学习

README.md

原文

This repo contains GANs review for topics of computer vision and time series

News

[2021/07/11] Our preprint "Generative Adversarial Networks in Time Series: A Survey and Taxonomy", Eoin Brophy and Zhengwei Wang and Qi She and Tomas E. Ward is out. This work is currently in progress.

[2021/02/14] Our paper “Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy” Zhengwei Wang and Qi She and Tomas E. Ward (arxiv version) has been published at ACM Computing Surveys,and we will continue to polish this work into the 5th version. Details of selected papers and codes can refer to GAN_CV folder.

[2020/11/24] Our paper “Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy” Zhengwei Wang and Qi She and Tomas E. Ward gets acceptted into ACM Computing Surveys,and we will continue to polish this work into the 5th version.

[2020/06/20] We have updated our 4th version of GAN survey for computer vision paper ! It inlcudes more recent GANs proposed at CVPR, ICCV 2019/2020, more intuitive visualization of GAN Taxonomy.

[2020/10/04] GANs related to our latest paper will be updated shortly.

Generative Adversarial Networks in Computer Vision

A Survey and Taxonomy of the Recent GANs Development in computer vision. Please refer to the details in recent review paper “Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy” Zhengwei Wang and Qi She and Tomas E. Ward (arxiv version). We also provide a list of papers related to GANs on computer vision in the GAN_CV.csv file.

If you find this useful in your research, please consider citing:

@article{wang2021generative,
  title={Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy},
  author={Wang, Zhengwei and She, Qi and Ward, Tomas E},
  journal={ACM Computing Surveys (CSUR)},
  volume={54},
  number={2},
  pages={1--38},
  year={2021},
  publisher={ACM New York, NY, USA}
}

We have classified the two GAN-variants research lines based on recent GAN developments, below we provide a summary and the demo code of these models. We have tested the codes below and tried to summary some of lightweight and easy-to-reuse module of state-of-the-art GANs.

Architecture-variant GANs

LAPGAN:
https://github.com/jimfleming/LAPGAN (TensorFlow)
https://github.com/AaronYALai/Generative_Adversarial_Networks_PyTorch (PyTorch)

DCGAN:
https://github.com/carpedm20/DCGAN-tensorflow (TensorFlow)
https://github.com/last-one/DCGAN-Pytorch (PyTorch)

BEGAN:
https://github.com/carpedm20/BEGAN-tensorflow (TensorFlow)
https://github.com/anantzoid/BEGAN-pytorch (PyTorch)

PROGAN:
https://github.com/tkarras/progressive_growing_of_gans (TensorFlow)
https://github.com/nashory/pggan-pytorch (PyTorch)

SAGAN:
https://github.com/brain-research/self-attention-gan (TensorFlow)
https://github.com/heykeetae/Self-Attention-GAN (PyTorch)

BigGAN:
https://github.com/taki0112/BigGAN-Tensorflow (TensorFlow)
https://github.com/ajbrock/BigGAN-PyTorch (PyTorch)

Your Local GAN:
https://github.com/giannisdaras/ylg (TensorFlow)
https://github.com/188zzoon/Your-Local-GAN (PyTorch)

AutoGAN:
https://github.com/VITA-Group/AutoGAN (PyTorch)

MSG-GAN:
https://github.com/akanimax/msg-stylegan-tf (TensorFlow)
https://github.com/akanimax/msg-gan-v1 (PyTorch)

Loss-variant GANs

WGAN:
https://github.com/ChengBinJin/WGAN-TensorFlow (TensorFlow)
https://github.com/Zeleni9/pytorch-wgan (PyTorch)

WGAN-GP:
https://github.com/changwoolee/WGAN-GP-tensorflow (TensorFlow)
https://github.com/caogang/wgan-gp (PyTorch)

LSGAN:
https://github.com/xudonmao/LSGAN (TensorFlow)
https://github.com/meliketoy/LSGAN.pytorch (PyTorch)

f-GAN:
https://github.com/LynnHo/f-GAN-Tensorflow (TensorFlow)

UGAN:
https://github.com/gokul-uf/TF-Unrolled-GAN (TensorFlow)
https://github.com/andrewliao11/unrolled-gans (PyTorch)

LS-GAN:
https://github.com/maple-research-lab/lsgan-gp-alt (TensorFlow)
https://github.com/maple-research-lab/glsgan-gp (PyTorch)

MRGAN:
https://github.com/wiseodd/generative-models/tree/master/GAN/mode_regularized_gan (TensorFlow and PyTorch)

Geometric GAN:
https://github.com/lim0606/pytorch-geometric-gan (PyTorch)

RGAN:
https://github.com/AlexiaJM/RelativisticGAN (TensorFlow and PyTorch)

SN-GAN:
https://github.com/taki0112/Spectral_Normalization-Tensorflow (TensorFlow) https://github.com/christiancosgrove/pytorch-spectral-normalization-gan (PyTorch)

RealnessGAN:
https://github.com/taki0112/RealnessGAN-Tensorflow (TensorFlow)
https://github.com/kam1107/RealnessGAN (PyTorch)

Sphere GAN:
https://github.com/taki0112/SphereGAN-Tensorflow (TensorFlow)
https://github.com/Dotori-HJ/SphereGAN-Pytorch-implementation (PyTorch)

Self-supervised GAN:
https://github.com/zhangqianhui/Self-Supervised-GANs (TensorFlow)
https://github.com/vandit15/Self-Supervised-Gans-Pytorch (PyTorch)

GAN Review for Time Series

A Survey and Taxonomy of the Recent GANs Development in time series. Please refer to the details in recent review paper "Generative Adversarial Networks in Time Series: A Survey and Taxonomy", Eoin Brophy and Zhengwei Wang and Qi She and Tomas E. Ward. This work is currently in progress.

If you find this useful in your research, please consider citing:

@article{brophy2021generative,
  title={Generative adversarial networks in time series: A survey and taxonomy},
  author={Brophy, Eoin and Wang, Zhengwei and She, Qi and Ward, Tomas},
  journal={arXiv preprint arXiv:2107.11098},
  year={2021}
}

Datasets

Unlike computer vision having lots of well-known and large-scale benchmarking datasets, time series benchmarking datasets are limited due to generalization and some privacy issues especially for clinical data. Below we provide some resources of well-known time series datasets. Hopefully it is useful. Feel free to suggest any well-known time series datasets to this repo by opening new issue. We will review it and add it to the list! We hope this can help push the time series research forward!

Discrete-variant GANs

Continuous-variant GANs