Few-shot learning with unsupervised part discovery and part-aligned similarity
文献类型:期刊论文
作者 | Chen, Wentao1,3; Zhang, Zhang2,3,4; Wang, Wei3,4; Wang, Liang3,4; Wang, Zilei1; Tan, Tieniu1,3,4 |
刊名 | PATTERN RECOGNITION |
出版日期 | 2023 |
卷号 | 133页码:12 |
ISSN号 | 0031-3203 |
关键词 | Few-shot learning Self-supervised learning Part discovery network Part-aligned similarity |
DOI | 10.1016/j.patcog.2022.108986 |
通讯作者 | Zhang, Zhang(zzhang@nlpr.ia.ac.cn) |
英文摘要 | Few-shot learning aims to recognize novel concepts with only a few examples. To this end, previous studies resort to acquiring a strong inductive bias via meta-learning on a group of similar tasks, which however needs a large labeled base dataset to sample training tasks. In this paper, we show that such inductive bias can be learned from a flat collection of unlabeled images, and instantiated as transfer-able representations among seen and unseen classes. Specifically, we propose a novel unsupervised Part Discovery Network (PDN) to learn transferable representations from unlabeled images, which automat-ically selects the most discriminative part from an input image and then maximizes its similarities to the global view of the input and other neighbors with similar semantics. To better leverage the learned representations for few-shot learning, we further propose Part-Aligned Similarity (PAS), the key of which is to measure image similarities based on a set of discriminative and aligned parts. We conduct extensive studies on five popular few-shot learning datasets to evaluate our approach. The experimental results show that our approach outperforms previous unsupervised methods by a large margin and is even com-parable with state-of-the-art supervised methods.(c) 2022 Elsevier Ltd. All rights reserved. |
资助项目 | National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[61836008] ; National Natural Science Foundation of China[61976214] ; National Natural Science Foundation of China[62076078] ; CAS -AIR |
WOS研究方向 | Computer Science ; Engineering |
语种 | 英语 |
出版者 | ELSEVIER SCI LTD |
WOS记录号 | WOS:000863094500003 |
资助机构 | National Natural Science Foundation of China ; CAS -AIR |
源URL | [http://ir.ia.ac.cn/handle/173211/50311] |
专题 | 自动化研究所_智能感知与计算研究中心 |
通讯作者 | Zhang, Zhang |
作者单位 | 1.Univ Sci & Technol China, Hefei, Peoples R China 2.Inst Automat, 95 Zhongguancun East Rd, Beijing, Peoples R China 3.CASIA, NLPR, Ctr Res Intelligent Percept & Comp, Beijing, Peoples R China 4.Univ Chinese Acad Sci, Beijing, Peoples R China |
推荐引用方式 GB/T 7714 | Chen, Wentao,Zhang, Zhang,Wang, Wei,et al. Few-shot learning with unsupervised part discovery and part-aligned similarity[J]. PATTERN RECOGNITION,2023,133:12. |
APA | Chen, Wentao,Zhang, Zhang,Wang, Wei,Wang, Liang,Wang, Zilei,&Tan, Tieniu.(2023).Few-shot learning with unsupervised part discovery and part-aligned similarity.PATTERN RECOGNITION,133,12. |
MLA | Chen, Wentao,et al."Few-shot learning with unsupervised part discovery and part-aligned similarity".PATTERN RECOGNITION 133(2023):12. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
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。