Few-shot learning with unsupervised part discovery and part-aligned similarity

doi:10.1016/j.patcog.2022.108986

CORC > 自动化研究所 > 中国科学院自动化研究所 > 智能感知与计算研究中心

	Few-shot learning with unsupervised part discovery and part-aligned similarity
	Chen, Wentao 2,3; Zhang, Zhang 1,2,4; Wang, Wei 2,4; Wang, Liang 2,4; Wang, Zilei 3; Tan, Tieniu 2,3,4
刊名	PATTERN RECOGNITION
	2023
卷号	133 页码:12
关键词	Few-shot learning Self-supervised learning Part discovery network Part-aligned similarity
ISSN号	0031-3203
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
内容类型	期刊论文
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.Inst Automat, 95 Zhongguancun East Rd, Beijing, Peoples R China 2.CASIA, NLPR, Ctr Res Intelligent Percept & Comp, Beijing, Peoples R China 3.Univ Sci & Technol China, Hefei, 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.