Survey of generative adversarial network
Firstly, the basic theory, application scenarios and current state of research of GAN (generative adversarial network) were introduced, and the problems need to be improved were listed.Then, recent research, improvement mechanism and model features in 2 categories and 7 subcategories revolved around...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
POSTS&TELECOM PRESS Co., LTD
2021-08-01
|
| Series: | 网络与信息安全学报 |
| Subjects: | |
| Online Access: | http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2021080 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841529882625966080 |
|---|---|
| author | Zhenglong WANG Baowen ZHANG |
| author_facet | Zhenglong WANG Baowen ZHANG |
| author_sort | Zhenglong WANG |
| collection | DOAJ |
| description | Firstly, the basic theory, application scenarios and current state of research of GAN (generative adversarial network) were introduced, and the problems need to be improved were listed.Then, recent research, improvement mechanism and model features in 2 categories and 7 subcategories revolved around 3 points (improving model training efficiency, improving the quality of generated samples, and reducing the possibility of model collapse) were generalized and summarized.Finally, 3 future research directions were discussed. |
| format | Article |
| id | doaj-art-5d42e3c9ab044e53aad17cf2fb318dc7 |
| institution | Kabale University |
| issn | 2096-109X |
| language | English |
| publishDate | 2021-08-01 |
| publisher | POSTS&TELECOM PRESS Co., LTD |
| record_format | Article |
| series | 网络与信息安全学报 |
| spelling | doaj-art-5d42e3c9ab044e53aad17cf2fb318dc72025-01-15T03:15:04ZengPOSTS&TELECOM PRESS Co., LTD网络与信息安全学报2096-109X2021-08-017688559567769Survey of generative adversarial networkZhenglong WANGBaowen ZHANGFirstly, the basic theory, application scenarios and current state of research of GAN (generative adversarial network) were introduced, and the problems need to be improved were listed.Then, recent research, improvement mechanism and model features in 2 categories and 7 subcategories revolved around 3 points (improving model training efficiency, improving the quality of generated samples, and reducing the possibility of model collapse) were generalized and summarized.Finally, 3 future research directions were discussed.http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2021080generative adversarial networkgenerative modeldeep learningmode collapsedistribution similarity measurementrobustness of artificial neural network |
| spellingShingle | Zhenglong WANG Baowen ZHANG Survey of generative adversarial network 网络与信息安全学报 generative adversarial network generative model deep learning mode collapse distribution similarity measurement robustness of artificial neural network |
| title | Survey of generative adversarial network |
| title_full | Survey of generative adversarial network |
| title_fullStr | Survey of generative adversarial network |
| title_full_unstemmed | Survey of generative adversarial network |
| title_short | Survey of generative adversarial network |
| title_sort | survey of generative adversarial network |
| topic | generative adversarial network generative model deep learning mode collapse distribution similarity measurement robustness of artificial neural network |
| url | http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2021080 |
| work_keys_str_mv | AT zhenglongwang surveyofgenerativeadversarialnetwork AT baowenzhang surveyofgenerativeadversarialnetwork |