Knowledge Commons of Institute of Automation,CAS
Meta-Prototypical Learning for Domain-Agnostic Few-Shot Recognition | |
Wang RQ(王瑞琪)1,2; Zhang XY(张煦尧)1,2; Liu CL(刘成林)1,2,3 | |
发表期刊 | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS |
ISSN | 2162-237X |
2021-06-04 | |
页码 | 1-7 |
摘要 | Few-shot learning (FSL) aims to classify novel images based on a few labeled samples with the help of meta-knowledge. Most previous works address this problem based on the hypothesis that the training set and testing set are from the same domain, which is not realistic for some real-world applications. Thus, we extend FSL to domain-agnostic few-shot recognition, where the domain of the testing task is unknown. In domain-agnostic few-shot recognition, the model is optimized on data from one domain and evaluated on tasks from different domains. Previous methods for FSL mostly focus on learning general features or adapting to few-shot tasks effectively. They suffer from inappropriate features or complex adaptation in domain-agnostic few-shot recognition. In this brief, we propose meta-prototypical learning to address this problem. In particular, a meta-encoder is optimized to learn the general features. Different from the traditional prototypical learning, the meta encoder can effectively adapt to few-shot tasks from different domains by the traces of the few labeled examples. Experiments on many datasets demonstrate that meta-prototypical learning performs competitively on traditional few-shot tasks, and on few-shot tasks from different domains, meta-prototypical learning outperforms related methods. |
关键词 | domain-agnostic few-shot recognition image classification meta-learning prototypical learning |
DOI | 10.1109/TNNLS.2021.3083650 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Key Research and Development Program of China[2018AAA0101400] ; National Key Research and Development Program of China[2018AAA0101400] |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000732371300001 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
七大方向——子方向分类 | 模式识别基础 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/46969 |
专题 | 多模态人工智能系统全国重点实验室_模式分析与学习 |
通讯作者 | Liu CL(刘成林) |
作者单位 | 1.中国科学院自动化研究所模式识别国家重点实验室 2.中国科学院大学人工智能学院 3.中国科学院脑科学与智能技术卓越创新中心 |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Wang RQ,Zhang XY,Liu CL. Meta-Prototypical Learning for Domain-Agnostic Few-Shot Recognition[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2021:1-7. |
APA | Wang RQ,Zhang XY,&Liu CL.(2021).Meta-Prototypical Learning for Domain-Agnostic Few-Shot Recognition.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,1-7. |
MLA | Wang RQ,et al."Meta-Prototypical Learning for Domain-Agnostic Few-Shot Recognition".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2021):1-7. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Meta-Prototypical_Le(1403KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论