CoChat

A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications

Gui, Jie, Sun, Zhenan, Wen, Yonggang, Tao, Dacheng, Ye, Jieping · 2023 · IEEE Transactions on Knowledge and Data Engineering

The DOI matches its Crossref record; 332 of the 332 references it cites were found in a registry or an index.

Abstract

Generative adversarial networks (GANs) have recently become a hot research topic; however, they have been studied since 2014, and a large number of algorithms have been proposed. Nevertheless, few comprehensive studies explain the connections among different GAN variants and how they have evolved. In this paper, we attempt to provide a review of the various GAN methods from the perspectives of algorithms, theory, and applications. First, the motivations, mathematical representations, and structures of most GAN algorithms are introduced in detail, and we compare their commonalities and differences. Second, theoretical issues related to GANs are investigated. Finally, typical applications of GANs in image processing and computer vision, natural language processing, music, speech and audio, the medical field, and data science are discussed.

Overview

Integrity signals

Registry

Crossref · 10.1109/tkde.2021.3130191

Cites

332 of 332 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 332 references

Research works printed but not linked: 17

  1. Schmidhuber, 1990, Making the world differentiable: On using fully recurrent self-supervised neural networks for dynamic reinforcement learning and planning in non-stationary environments, Inst. Comput. Sci., Tech. Univ. Munich, Germany, FKI-126, Tech. Rep.
  2. Schmidhuber, 2009, Art & science as by-products of the search for novel patterns, or data compressible in unknown yet learnable ways, Edizioni, 98
  3. Goodfellow, Generative adversarial nets, 2672
  4. 10.1016/S0364-0213(85)80012-4 · doi:10.1016/s0364-0213(85)80012-4 · Paper page
  5. Gauthier, 2014, Conditional generative adversarial nets for convolutional face generation, Class Project for Stanford CS231N: Convolutional Neural Netw. Vis. Recognit., Winter semester, 2014
  6. Yao, 3D-aware scene manipulation via inverse graphics, 1887
  7. Gong, Twin auxilary classifiers GAN, 1328
  8. Uppal, Nonparametric density estimation & convergence of GANs under besov IPM losses, 9086
  9. Mroueh, Sobolev GAN
  10. Goodfellow, 2016, Deep Learning
  11. 10.1109/ICCV.2019.00460 · DOI · Paper page
  12. Singh, Nonparametric density estimation with adversarial losses, 10246
  13. Nagarajan, Theoretical insights into memorization in GANs, 1
  14. Cao, Learning a high fidelity pose invariant model for high-resolution face frontalization, 2867
  15. Zhang, Generating text via adversarial training, 1
  16. d’Autume, Training language GANs from scratch, 4302
  17. Rao, Answer-based adversarial training for generating clarification questions, 1

Metadata

Authors
Gui, J., Sun, Z., Wen, Y., Tao, D., & Ye, J.
Affiliations
  • University of Michigan (US)
  • Chinese Academy of Sciences (CN)
  • Nanyang Technological University (SG)
  • The University of Sydney (AU)
Venue
IEEE Transactions on Knowledge and Data Engineering
Published
2023-04-01
Volume
35
Issue
4
Pages
3313-3332
ISSN
  • 1041-4347 (ISSN-L)
  • 1558-2191
  • 2326-3865
OpenAlex
W3216759837
Cited by
1,231
References
329
Citations by year
2026: 181 · 2025: 304 · 2024: 341 · 2023: 216
FWCI
65.28
Type
journal article
Language
en
Open access
closed
Locations
  • IEEE Transactions on Knowledge and Data Engineering (publishedVersion)
  • DR-NTU (Nanyang Technological University) (submittedVersion)
Funders
  • National Natural Science Foundation of China (62172090, 62172089)
  • National Key R&D Project of China (2021QY2102)
  • CAAI-Huawei MindSpore Open Fund
  • Alibaba Innovative Research Program
  • Fundamental Research Funds for the Central Universities (2242022R10071)
  • National Research Foundation Singapore
  • Jiangsu Provincial Double-Innovation Doctor Program (JSSCBS20210075)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
  • Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
Keywords
generative adversarial networks, GAN variants, generative models, image generation, image processing, natural language generation, music generation, medical image synthesis, data science applications

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.