Research on Generative Adversarial Networks Using Twins Attention Mechanism
Generative adversarial network (GAN) has become a research hotspot in generation model, since it can generate realistic images. To cope with the problem that the GAN cannot effectively capture the dependency between local and global features of the image and the dependency between different classes,...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press
2020-05-01
|
| Series: | Jisuanji kexue yu tansuo |
| Subjects: | |
| Online Access: | http://fcst.ceaj.org/CN/abstract/abstract2196.shtml |
| _version_ | 1818886145666187264 |
|---|---|
| author | WU Suishuo, YANG Jinfu, SHAN Yi, XU Bingbing |
| author_facet | WU Suishuo, YANG Jinfu, SHAN Yi, XU Bingbing |
| author_sort | WU Suishuo, YANG Jinfu, SHAN Yi, XU Bingbing |
| collection | DOAJ |
| description | Generative adversarial network (GAN) has become a research hotspot in generation model, since it can generate realistic images. To cope with the problem that the GAN cannot effectively capture the dependency between local and global features of the image and the dependency between different classes, this paper proposes a new generation model, named twins attention mechanism based generative adversarial network (TAGAN). Driven by twins attention mechanism, the real natural image is modeled by simulating the dependencies between local and global features and the dependencies between categories to create realistic fake images. TAGAN has feature attention and channel attention. The feature attention learns the correlation between similar features by selectively aggregating features. The channel attention learns the internal dependencies of each channel by integrating the relevant features of each channel dimension. The experiments implemented on the MNIST, CIFAR10 and CelebA64 datasets demonstrate that the proposed model is effective. |
| first_indexed | 2024-12-19T16:16:41Z |
| format | Article |
| id | doaj.art-bbd59e0d95094750b3de782c9e511d40 |
| institution | Directory Open Access Journal |
| issn | 1673-9418 |
| language | zho |
| last_indexed | 2024-12-19T16:16:41Z |
| publishDate | 2020-05-01 |
| publisher | Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press |
| record_format | Article |
| series | Jisuanji kexue yu tansuo |
| spelling | doaj.art-bbd59e0d95094750b3de782c9e511d402022-12-21T20:14:36ZzhoJournal of Computer Engineering and Applications Beijing Co., Ltd., Science PressJisuanji kexue yu tansuo1673-94182020-05-0114583384010.3778/j.issn.1673-9418.1905026Research on Generative Adversarial Networks Using Twins Attention MechanismWU Suishuo, YANG Jinfu, SHAN Yi, XU Bingbing01. Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China 2. Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing 100124, ChinaGenerative adversarial network (GAN) has become a research hotspot in generation model, since it can generate realistic images. To cope with the problem that the GAN cannot effectively capture the dependency between local and global features of the image and the dependency between different classes, this paper proposes a new generation model, named twins attention mechanism based generative adversarial network (TAGAN). Driven by twins attention mechanism, the real natural image is modeled by simulating the dependencies between local and global features and the dependencies between categories to create realistic fake images. TAGAN has feature attention and channel attention. The feature attention learns the correlation between similar features by selectively aggregating features. The channel attention learns the internal dependencies of each channel by integrating the relevant features of each channel dimension. The experiments implemented on the MNIST, CIFAR10 and CelebA64 datasets demonstrate that the proposed model is effective.http://fcst.ceaj.org/CN/abstract/abstract2196.shtmldeep learninggenerative adversarial network (gan)generative modelagainst learningattention mechanism |
| spellingShingle | WU Suishuo, YANG Jinfu, SHAN Yi, XU Bingbing Research on Generative Adversarial Networks Using Twins Attention Mechanism Jisuanji kexue yu tansuo deep learning generative adversarial network (gan) generative model against learning attention mechanism |
| title | Research on Generative Adversarial Networks Using Twins Attention Mechanism |
| title_full | Research on Generative Adversarial Networks Using Twins Attention Mechanism |
| title_fullStr | Research on Generative Adversarial Networks Using Twins Attention Mechanism |
| title_full_unstemmed | Research on Generative Adversarial Networks Using Twins Attention Mechanism |
| title_short | Research on Generative Adversarial Networks Using Twins Attention Mechanism |
| title_sort | research on generative adversarial networks using twins attention mechanism |
| topic | deep learning generative adversarial network (gan) generative model against learning attention mechanism |
| url | http://fcst.ceaj.org/CN/abstract/abstract2196.shtml |
| work_keys_str_mv | AT wusuishuoyangjinfushanyixubingbing researchongenerativeadversarialnetworksusingtwinsattentionmechanism |