Zero-Shot Embedding via Regularization-Based Recollection and Residual Familiarity Processes

doi:10.1109/TSMC.2021.3102834

	Zero-Shot Embedding via Regularization-Based Recollection and Residual Familiarity Processes
	Lyu, Mengyao 1; Han, Hu 2,3; Bai, Xiangzhi 4,5,6
	2021-08-16
发表期刊	IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
ISSN	2168-2216
页码	18
摘要	The goal of zero-shot learning (ZSL) is to transfer knowledge learned from seen classes during training to unseen classes for testing, with the help of auxiliary information, such as attributes and descriptions. Most of the existing methods view ZSL as a label-embedding problem, in which class and image representations are embedded to a common space. However, many methods either show a bias toward seen classes caused by the projection domain-shift problem, or sacrifice the performance of seen classes to generalize to unseen ones. In this article, we present an embedding approach for ZSL, which is motivated by human recognition memory, namely, recollection and familiarity (R&F). We propose a decoder to regularize the nonlinear mapping between the semantic space and the visual space, which represents the reasonable recollection process, and use a residual block to refine the recognition ability for seen classes, which indicates the familiarity process. R&F can generalize well to unseen classes, while retaining the discriminative ability for the seen classes. Extensive experiments are conducted on Animals with Attribute (AwA1), Animals with Attributes 2 (AwA2), Attribute Pascal&Yahoo (aPY), SUN Attribute (SUN), Caltech-UCSD-Birds 200-2011 (CUB), and ImageNet databases. As qualitative and quantitative results show, the proposed approach outperforms state-of-the-art embedding-based methods by a large margin and significantly alleviates the projection domain-shift problem.
关键词	Embedding-based method image classification knowledge transfer zero-shot learning (ZSL)
DOI	10.1109/TSMC.2021.3102834
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2019YFB1311301] ; National Natural Science Foundation of China[U1736217] ; Youth Innovation Promotion Association CAS[2018135]
WOS研究方向	Automation & Control Systems ; Computer Science
WOS类目	Automation & Control Systems ; Computer Science, Cybernetics
WOS记录号	WOS:000732300600001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/17945
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Bai, Xiangzhi
作者单位	1.Beihang Univ, Image Proc Ctr, Beijing 102206, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 3.Peng Cheng Lab, Shenzhen 518055, Peoples R China 4.Beihang Univ, Image Proc Ctr, Beijing 102206, Peoples R China 5.Beihang Univ, State Key Lab Virtual Real Technol & Syst, Beijing 100191, Peoples R China 6.Beihang Univ, Adv Innovat Ctr Biomed Engn, Beijing 100083, Peoples R China
推荐引用方式 GB/T 7714	Lyu, Mengyao,Han, Hu,Bai, Xiangzhi. Zero-Shot Embedding via Regularization-Based Recollection and Residual Familiarity Processes[J]. IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS,2021:18.
APA	Lyu, Mengyao,Han, Hu,&Bai, Xiangzhi.(2021).Zero-Shot Embedding via Regularization-Based Recollection and Residual Familiarity Processes.IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS,18.
MLA	Lyu, Mengyao,et al."Zero-Shot Embedding via Regularization-Based Recollection and Residual Familiarity Processes".IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS (2021):18.