Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2020 Aug 1:2020:1459107.
doi: 10.1155/2020/1459107. eCollection 2020.

Generative Adversarial Network Technologies and Applications in Computer Vision

Lianchao Jin  1 , Fuxiao Tan  1 , Shengming Jiang  1
Affiliations
Review

Generative Adversarial Network Technologies and Applications in Computer Vision

Lianchao Jin et al. Comput Intell Neurosci. .

Abstract

Computer vision is one of the hottest research fields in deep learning. The emergence of generative adversarial networks (GANs) provides a new method and model for computer vision. The idea of GANs using the game training method is superior to traditional machine learning algorithms in terms of feature learning and image generation. GANs are widely used not only in image generation and style transfer but also in the text, voice, video processing, and other fields. However, there are still some problems with GANs, such as model collapse and uncontrollable training. This paper deeply reviews the theoretical basis of GANs and surveys some recently developed GAN models, in comparison with traditional GAN models. The applications of GANs in computer vision include data enhancement, domain transfer, high-quality sample generation, and image restoration. The latest research progress of GANs in artificial intelligence (AI) based security attack and defense is introduced. The future development of GANs in computer vision is also discussed at the end of the paper with possible applications of AI in computer vision.

PubMed Disclaimer

Conflict of interest statement

The authors declare that there are no conflicts of interest regarding the publication of this paper.

Figures

Figure 1
Figure 1
GAN network architecture.
Figure 2
Figure 2
PAN network structure [40].
Figure 3
Figure 3
MAD-GAN model structure.
Figure 4
Figure 4
Comparison of stackGAN with its improved version [50] (StackGAN-v1 is original stackGAN while StackGAN-v2 is the stackGAN++ model; the latter can generate more realistic and details samples).
Figure 5
Figure 5
Image of hemangioma generated by CGAN [56].
Figure 6
Figure 6
StarGAN generation image [71].
Figure 7
Figure 7
Encrypted communication system.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Pan Z., Yu W., Yi X., Khan A., Yuan F., Zheng Y. Recent progress on generative adversarial networks (GANs): a survey. IEEE Access. 2019;7:36322–36333. doi: 10.1109/access.2019.2905015. - DOI
    1. Liu S. Face aging with contextual generative adversarial nets. Proceedings of the ACM; November 2017; Singapore. pp. 82–90.
    1. Hu D., Wang L., Jiang W., Zheng S., Li B. A novel image steganography method via deep convolutional generative adversarial networks. IEEE Access. 2018;6:38303–38314. doi: 10.1109/access.2018.2852771. - DOI
    1. Odena A., Olah C., Shlens J. Conditional image synthesis with auxiliary classifier GANs. Proceedings of the 34th International Conference Machine Learning (PMLR); 2017; Sydney, Australia. pp. 2642–2651. https://arxiv.org/abs/1610.09585.
    1. Kim K., Myung H. Autoencoder-combined generative adversarial networks for synthetic image data generation and detection of jellyfish swarm. IEEE Access. 2018;6:54207–54214. doi: 10.1109/access.2018.2872025. - DOI

LinkOut - more resources