Recent Advances of Generative Adversarial Networks in Computer Vision
The appearance of generative adversarial networks (GAN) provides a new approach and framework for computer vision. Compared with traditional machine learning algorithms, GAN works via adversarial training concept and is more powerful in both feature learning and representation. GAN also exhibits som...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8576508/ |
id |
doaj-82d21c9bd8ef495baa5c91e1d9337b2b |
---|---|
record_format |
Article |
spelling |
doaj-82d21c9bd8ef495baa5c91e1d9337b2b2021-03-29T22:35:56ZengIEEEIEEE Access2169-35362019-01-017149851500610.1109/ACCESS.2018.28868148576508Recent Advances of Generative Adversarial Networks in Computer VisionYang-Jie Cao0https://orcid.org/0000-0002-1170-4340Li-Li Jia1https://orcid.org/0000-0001-5662-2210Yong-Xia Chen2Nan Lin3Cong Yang4Bo Zhang5Zhi Liu6Xue-Xiang Li7Hong-Hua Dai8School of Software Engineering, Zhengzhou University, Zhengzhou, ChinaSchool of Software Engineering, Zhengzhou University, Zhengzhou, ChinaSchool of Software Engineering, Zhengzhou University, Zhengzhou, ChinaSchool of Software Engineering, Zhengzhou University, Zhengzhou, ChinaSchool of Software Engineering, Zhengzhou University, Zhengzhou, ChinaSchool of Software Engineering, Zhengzhou University, Zhengzhou, ChinaDepartment of Mathematical and Systems Engineering, Shizuoka University, Shizuoka, JapanSchool of Software Engineering, Zhengzhou University, Zhengzhou, ChinaInstitute of Intelligent Systemsm, Deakin University, Geelong, VIC, AustraliaThe appearance of generative adversarial networks (GAN) provides a new approach and framework for computer vision. Compared with traditional machine learning algorithms, GAN works via adversarial training concept and is more powerful in both feature learning and representation. GAN also exhibits some problems, such as non-convergence, model collapse, and uncontrollability due to high degree of freedom. How to improve the theory of GAN and apply it to computer-vision-related tasks have now attracted much research efforts. In this paper, recently proposed GAN models and their applications in computer vision are systematically reviewed. In particular, we firstly survey the history and development of generative algorithms, the mechanism of GAN, its fundamental network structures, and theoretical analysis of the original GAN. Classical GAN algorithms are then compared comprehensively in terms of the mechanism, visual results of generated samples, and Frechet Inception Distance. These networks are further evaluated from network construction, performance, and applicability aspects by extensive experiments conducted over public datasets. After that, several typical applications of GAN in computer vision, including high-quality samples generation, style transfer, and image translation, are examined. Finally, some existing problems of GAN are summarized and discussed and potential future research topics are forecasted.https://ieeexplore.ieee.org/document/8576508/Deep learninggenerative adversarial networks (GAN)computer vision (CV)image generationstyle transferimage inpainting |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yang-Jie Cao Li-Li Jia Yong-Xia Chen Nan Lin Cong Yang Bo Zhang Zhi Liu Xue-Xiang Li Hong-Hua Dai |
spellingShingle |
Yang-Jie Cao Li-Li Jia Yong-Xia Chen Nan Lin Cong Yang Bo Zhang Zhi Liu Xue-Xiang Li Hong-Hua Dai Recent Advances of Generative Adversarial Networks in Computer Vision IEEE Access Deep learning generative adversarial networks (GAN) computer vision (CV) image generation style transfer image inpainting |
author_facet |
Yang-Jie Cao Li-Li Jia Yong-Xia Chen Nan Lin Cong Yang Bo Zhang Zhi Liu Xue-Xiang Li Hong-Hua Dai |
author_sort |
Yang-Jie Cao |
title |
Recent Advances of Generative Adversarial Networks in Computer Vision |
title_short |
Recent Advances of Generative Adversarial Networks in Computer Vision |
title_full |
Recent Advances of Generative Adversarial Networks in Computer Vision |
title_fullStr |
Recent Advances of Generative Adversarial Networks in Computer Vision |
title_full_unstemmed |
Recent Advances of Generative Adversarial Networks in Computer Vision |
title_sort |
recent advances of generative adversarial networks in computer vision |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
The appearance of generative adversarial networks (GAN) provides a new approach and framework for computer vision. Compared with traditional machine learning algorithms, GAN works via adversarial training concept and is more powerful in both feature learning and representation. GAN also exhibits some problems, such as non-convergence, model collapse, and uncontrollability due to high degree of freedom. How to improve the theory of GAN and apply it to computer-vision-related tasks have now attracted much research efforts. In this paper, recently proposed GAN models and their applications in computer vision are systematically reviewed. In particular, we firstly survey the history and development of generative algorithms, the mechanism of GAN, its fundamental network structures, and theoretical analysis of the original GAN. Classical GAN algorithms are then compared comprehensively in terms of the mechanism, visual results of generated samples, and Frechet Inception Distance. These networks are further evaluated from network construction, performance, and applicability aspects by extensive experiments conducted over public datasets. After that, several typical applications of GAN in computer vision, including high-quality samples generation, style transfer, and image translation, are examined. Finally, some existing problems of GAN are summarized and discussed and potential future research topics are forecasted. |
topic |
Deep learning generative adversarial networks (GAN) computer vision (CV) image generation style transfer image inpainting |
url |
https://ieeexplore.ieee.org/document/8576508/ |
work_keys_str_mv |
AT yangjiecao recentadvancesofgenerativeadversarialnetworksincomputervision AT lilijia recentadvancesofgenerativeadversarialnetworksincomputervision AT yongxiachen recentadvancesofgenerativeadversarialnetworksincomputervision AT nanlin recentadvancesofgenerativeadversarialnetworksincomputervision AT congyang recentadvancesofgenerativeadversarialnetworksincomputervision AT bozhang recentadvancesofgenerativeadversarialnetworksincomputervision AT zhiliu recentadvancesofgenerativeadversarialnetworksincomputervision AT xuexiangli recentadvancesofgenerativeadversarialnetworksincomputervision AT honghuadai recentadvancesofgenerativeadversarialnetworksincomputervision |
_version_ |
1724191281058414592 |