您好，欢迎访问北京市农林科学院 机构知识库！
北京市农林科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Domain-adaptive graph neural network for few-shot learning

文献类型： 外文期刊

作者： Yang, Zhankui 1 ; Li, Wenyong 2 ; Zheng, Tengfei 2 ; Lv, Jiawei 2 ; Yang, Xinting 2 ; Ding, Zhiming 1 ;

作者机构： 1.Beijing Univ Technol, Coll Comp Sci & Technol, Beijing 100124, Peoples R China

2.Natl Engn Res Ctr Informat Technol Agr, Beijing 100089, Peoples R China

3.Chinese Acad Sci, Beijing 100190, Peoples R China

4.Shanghai Ocean Univ, Coll Informat, Shanghai 201306, Peoples R China

5.Zhongkai Univ Agr & Engn, Coll Informat Sci & Technol, Guangzhou 510225, Peoples R China

关键词： Few-shot classification; Domain adaptation; Domain-attention mechanism; Similarity transformation

期刊名称：KNOWLEDGE-BASED SYSTEMS （ 影响因子：8.8； 五年影响因子：8.6 ）

ISSN： 0950-7051

年卷期： 2023 年 275 卷

页码：

收录情况： SCI

摘要： The task of few-shot classification (FSC) is to build a model to discriminate novel categories that do not present in training categories with limited labeled samples. However, in many applications, the training categories and novel categories are assumed to come from the same domain. Existing few-shot classification algorithms achieve promising performance in a single domain, but often fail to generalize to unseen domains because of the different feature distribution across domains. The main goal of this work is to propose an effective recognition model that can work on various image domains with domain shift. Specifically, we propose to construct a new domain-attention mechanism with some adapters based on the squeeze-and-excitation network architectures. The proposed network processes multiple domains simultaneously and all parameters are shared across domains. In addition, because of the large discrepancy in feature distributions among different domains, similarity transformation layers are used to reduce the differences in the feature distributions in the training stage. Extensive experiments were conducted to validate the domain generalization capability (GC) of this model on four FSC datasets: mini-ImageNet, Cars, CUB-200-2011, and Simpsons Characters Data. The results show that the presented method has excellent performances on various datasets across diverse domains.& COPY; 2023 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：北京市农林科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台