| ZHAO Wencang(赵文仓),LI Ming,QIN Wenqian.[J].高技术通讯(英文),2022,28(2):164~171 |
|
| Task-adaptation graph network for few-shot learning |
| |
| DOI：10.3772/j.issn.1006-6748.2022.02.006 |
| 中文关键词: |
| 英文关键词: meta-learning, image classification, graph neural network (GNN), few-shot learning |
| 基金项目: |
| Author Name | Affiliation | | ZHAO Wencang(赵文仓) | (College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao 266061, P.R.China) | | LI Ming | (College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao 266061, P.R.China) | | QIN Wenqian | (College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao 266061, P.R.China) |
|
| Hits: 676 |
| Download times: 610 |
| 中文摘要: |
| |
| 英文摘要: |
| Numerous meta-learning methods focus on the few-shot learning issue, yet most of them assume that various tasks have a shared embedding space, so the generalization ability of the trained model is limited. In order to solve the aforementioned problem, a task-adaptive meta-learning method based on graph neural network (TAGN) is proposed in this paper, where the characterization ability of the original feature extraction network is ameliorated and the classification accuracy is remarkably improved. Firstly, a task-adaptation module based on the self-attention mechanism is employed, where the generalization ability of the model is enhanced on the new task. Secondly, images are classified in non-Euclidean domain, where the disadvantages of poor adaptability of the traditional distance function are overcome. A large number of experiments are conducted and the results show that the proposed methodology has a better performance than traditional task-independent classification methods on two real-word datasets. |
|
View Full Text
View/Add Comment Download reader |
| Close |
|
|
|
