A review on generative adversarial networks: algorithms, theory, and applications
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. However, few comprehensive studies exist explaining the connections among different GANs variants and how they have evolv...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/162749 |
| _version_ | 1826126014189666304 |
|---|---|
| author | Gui, Jie Sun, Zhenan Wen, Yonggang Tao, Dacheng Ye, Jieping |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Gui, Jie Sun, Zhenan Wen, Yonggang Tao, Dacheng Ye, Jieping |
| author_sort | Gui, Jie |
| collection | NTU |
| description | 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. However, few comprehensive studies exist explaining the connections among different GANs variants and how they have evolved. In this paper, we attempt to provide a review of the various GANs methods from the perspectives of algorithms, theory, and applications. First, the motivations, mathematical representations, and structures of most GANs 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, medical field, and data science are discussed. |
| first_indexed | 2024-10-01T06:45:49Z |
| format | Journal Article |
| id | ntu-10356/162749 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:45:49Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1627492022-11-08T01:25:14Z A review on generative adversarial networks: algorithms, theory, and applications Gui, Jie Sun, Zhenan Wen, Yonggang Tao, Dacheng Ye, Jieping School of Computer Science and Engineering Engineering::Computer science and engineering Deep Learning Generative Adversarial Networks 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. However, few comprehensive studies exist explaining the connections among different GANs variants and how they have evolved. In this paper, we attempt to provide a review of the various GANs methods from the perspectives of algorithms, theory, and applications. First, the motivations, mathematical representations, and structures of most GANs 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, medical field, and data science are discussed. This work was supported in part by the grant of the National Science Foundation of China under Grant 62172090; Jiangsu Provincial Double Innovation Doctor Program under Grant JSSCBS20210075. 2022-11-08T01:00:06Z 2022-11-08T01:00:06Z 2021 Journal Article Gui, J., Sun, Z., Wen, Y., Tao, D. & Ye, J. (2021). A review on generative adversarial networks: algorithms, theory, and applications. IEEE Transactions On Knowledge and Data Engineering, 1-20. https://dx.doi.org/10.1109/TKDE.2021.3130191 1041-4347 https://hdl.handle.net/10356/162749 10.1109/TKDE.2021.3130191 2-s2.0-85122776800 1 20 en IEEE Transactions on Knowledge and Data Engineering © 2021 IEEE. All rights reserved. |
| spellingShingle | Engineering::Computer science and engineering Deep Learning Generative Adversarial Networks Gui, Jie Sun, Zhenan Wen, Yonggang Tao, Dacheng Ye, Jieping A review on generative adversarial networks: algorithms, theory, and applications |
| title | A review on generative adversarial networks: algorithms, theory, and applications |
| title_full | A review on generative adversarial networks: algorithms, theory, and applications |
| title_fullStr | A review on generative adversarial networks: algorithms, theory, and applications |
| title_full_unstemmed | A review on generative adversarial networks: algorithms, theory, and applications |
| title_short | A review on generative adversarial networks: algorithms, theory, and applications |
| title_sort | review on generative adversarial networks algorithms theory and applications |
| topic | Engineering::Computer science and engineering Deep Learning Generative Adversarial Networks |
| url | https://hdl.handle.net/10356/162749 |
| work_keys_str_mv | AT guijie areviewongenerativeadversarialnetworksalgorithmstheoryandapplications AT sunzhenan areviewongenerativeadversarialnetworksalgorithmstheoryandapplications AT wenyonggang areviewongenerativeadversarialnetworksalgorithmstheoryandapplications AT taodacheng areviewongenerativeadversarialnetworksalgorithmstheoryandapplications AT yejieping areviewongenerativeadversarialnetworksalgorithmstheoryandapplications AT guijie reviewongenerativeadversarialnetworksalgorithmstheoryandapplications AT sunzhenan reviewongenerativeadversarialnetworksalgorithmstheoryandapplications AT wenyonggang reviewongenerativeadversarialnetworksalgorithmstheoryandapplications AT taodacheng reviewongenerativeadversarialnetworksalgorithmstheoryandapplications AT yejieping reviewongenerativeadversarialnetworksalgorithmstheoryandapplications |