Cooperative Coupled Generative Networks for Generalized Zero-Shot Learning
Compared with zero-shot learning (ZSL), the generalized zero-shot learning (GZSL) is more challenging since its test samples are taken from both seen and unseen classes. Most previous mapping-based methods perform well on ZSL, while their performance degrades on GZSL. To solve this problem, inspired...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9109281/ |
| _version_ | 1818428916077953024 |
|---|---|
| author | Liang Sun Junjie Song Ye Wang Baoyu Li |
| author_facet | Liang Sun Junjie Song Ye Wang Baoyu Li |
| author_sort | Liang Sun |
| collection | DOAJ |
| description | Compared with zero-shot learning (ZSL), the generalized zero-shot learning (GZSL) is more challenging since its test samples are taken from both seen and unseen classes. Most previous mapping-based methods perform well on ZSL, while their performance degrades on GZSL. To solve this problem, inspired by the ensemble learning, this paper proposes a model with cooperative coupled generative networks (CCGN). Firstly, to alleviate the hubness problem, the reverse visual feature space is taken as the embedding space, with the mapping achieved by a visual feature center generation network. To learn a proper visual representation of each class, we propose a coupled of generative networks, which cooperate with each other to synthesize a visual feature center template of the class. Secondly, to improve the generative ability of the coupled networks, we further employ a deeper network to generate. Meanwhile, to alleviate loss semantic information problem caused by multiple network layers, a residual module is employed. Thirdly, to mitigate overfitting and to increase scalability, an adversarial network is introduced to discriminate the generation of visual feature centers. Finally, a reconstruction network, which reverses the generation process, is employed to restrict the structural correlation between the generated visual feature center and the original semantic representation of each class. Extensive experiments on five benchmark datasets (AWA1, AWA2, CUB, SUN, APY) demonstrate that the proposed algorithm yields satisfactory results, as compared with the state-of-the-art methods. |
| first_indexed | 2024-12-14T15:09:13Z |
| format | Article |
| id | doaj.art-d469f7b085074afbabbf0fac42aed179 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T15:09:13Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-d469f7b085074afbabbf0fac42aed1792022-12-21T22:56:38ZengIEEEIEEE Access2169-35362020-01-01811928711929910.1109/ACCESS.2020.30003479109281Cooperative Coupled Generative Networks for Generalized Zero-Shot LearningLiang Sun0https://orcid.org/0000-0003-2794-8654Junjie Song1https://orcid.org/0000-0002-6486-521XYe Wang2https://orcid.org/0000-0002-6565-5484Baoyu Li3https://orcid.org/0000-0003-2457-9021College of Computer Science and Technology, Dalian University of Technology, Dalian, ChinaCollege of Computer Science and Technology, Dalian University of Technology, Dalian, ChinaCollege of Computer Science and Technology, Dalian University of Technology, Dalian, ChinaCollege of Computer Science and Technology, Dalian University of Technology, Dalian, ChinaCompared with zero-shot learning (ZSL), the generalized zero-shot learning (GZSL) is more challenging since its test samples are taken from both seen and unseen classes. Most previous mapping-based methods perform well on ZSL, while their performance degrades on GZSL. To solve this problem, inspired by the ensemble learning, this paper proposes a model with cooperative coupled generative networks (CCGN). Firstly, to alleviate the hubness problem, the reverse visual feature space is taken as the embedding space, with the mapping achieved by a visual feature center generation network. To learn a proper visual representation of each class, we propose a coupled of generative networks, which cooperate with each other to synthesize a visual feature center template of the class. Secondly, to improve the generative ability of the coupled networks, we further employ a deeper network to generate. Meanwhile, to alleviate loss semantic information problem caused by multiple network layers, a residual module is employed. Thirdly, to mitigate overfitting and to increase scalability, an adversarial network is introduced to discriminate the generation of visual feature centers. Finally, a reconstruction network, which reverses the generation process, is employed to restrict the structural correlation between the generated visual feature center and the original semantic representation of each class. Extensive experiments on five benchmark datasets (AWA1, AWA2, CUB, SUN, APY) demonstrate that the proposed algorithm yields satisfactory results, as compared with the state-of-the-art methods.https://ieeexplore.ieee.org/document/9109281/Zero-shot learninggeneralized zero-shot learninggenerative adversarial networkneural networkresidual module |
| spellingShingle | Liang Sun Junjie Song Ye Wang Baoyu Li Cooperative Coupled Generative Networks for Generalized Zero-Shot Learning IEEE Access Zero-shot learning generalized zero-shot learning generative adversarial network neural network residual module |
| title | Cooperative Coupled Generative Networks for Generalized Zero-Shot Learning |
| title_full | Cooperative Coupled Generative Networks for Generalized Zero-Shot Learning |
| title_fullStr | Cooperative Coupled Generative Networks for Generalized Zero-Shot Learning |
| title_full_unstemmed | Cooperative Coupled Generative Networks for Generalized Zero-Shot Learning |
| title_short | Cooperative Coupled Generative Networks for Generalized Zero-Shot Learning |
| title_sort | cooperative coupled generative networks for generalized zero shot learning |
| topic | Zero-shot learning generalized zero-shot learning generative adversarial network neural network residual module |
| url | https://ieeexplore.ieee.org/document/9109281/ |
| work_keys_str_mv | AT liangsun cooperativecoupledgenerativenetworksforgeneralizedzeroshotlearning AT junjiesong cooperativecoupledgenerativenetworksforgeneralizedzeroshotlearning AT yewang cooperativecoupledgenerativenetworksforgeneralizedzeroshotlearning AT baoyuli cooperativecoupledgenerativenetworksforgeneralizedzeroshotlearning |