Attribute-Induced Bias Eliminating for Transductive Zero-Shot Learning

doi:10.1109/TMM.2021.3074252

	Attribute-Induced Bias Eliminating for Transductive Zero-Shot Learning
	Yao, Hantao1 ; Min, Shaobo 2; Zhang, Yongdong 2; Xu, Changsheng1,3
发表期刊	IEEE TRANSACTIONS ON MULTIMEDIA
ISSN	1520-9210
	2022
卷号	24 页码:1933-1942
通讯作者	Yao, Hantao(hantao.yao@nlpr.ia.ac.cn)
摘要	Transductive zero-shot learning is designed to recognize unseen categories by aligning both visual and semantic information in a joint embedding space. Four types of domain biases exist in Transductive ZSL, i.e., visual bias and semantic bias in two domains, and two visual-semantic biases exist in the seen and unseen domains. However, the existing work has only focused on specific components of these topics, leading to severe semantic ambiguity during knowledge transfer. To solve this problem, we propose a novel attribute-induced bias eliminating (AIBE) module for Transductive ZSL. Specifically, for the visual bias between the two domains, the mean-teacher module is first used to bridge the visual representation discrepancy between the two domains using unsupervised learning and unlabeled images. Then, an attentional graph attribute embedding process is proposed to reduce the semantic bias between seen and unseen categories using a graph operation to describe the semantic relationship between categories. To reduce semantic-visual bias in the seen domain, we align the visual center of each category with the corresponding semantic attributes instead of with the individual visual data point, which preserves the semantic relationship in the embedding space. Finally, for the semantic-visual bias in the unseen domain, an unseen semantic alignment constraint is designed to align visual and semantic space using an unsupervised process. The evaluations on several benchmarks demonstrate the effectiveness of the proposed method, e.g., 82.8%/75.5%, 97.1%/82.5%, and 73.2%/52.1% for Conventional/Generalized ZSL settings for CUB, AwA2, and SUN datasets, respectively.
关键词	Semantics Visualization Bridges Training Knowledge transfer Image recognition Topology Transductive Zero-Shot Learning Graph Attribute Embedding Attribute-Induced Bias Eliminating Semantic-Visual Alignment
DOI	10.1109/TMM.2021.3074252
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2018AAA0102200] ; National Natural Science Foundation of China[61902399] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[U1836220] ; National Natural Science Foundation of China[U1705262] ; National Natural Science Foundation of China[61832002] ; National Natural Science Foundation of China[61720106006] ; National Natural Science Foundation of China[62002355] ; Beijing Natural Science Foundation[L201001] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-JSC039]
项目资助者	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Beijing Natural Science Foundation ; Key Research Program of Frontier Sciences, CAS
WOS研究方向	Computer Science ; Telecommunications
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications
WOS记录号	WOS:000778959200012
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类	机器学习
引用统计	被引频次：3[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/48336
专题	多模态人工智能系统全国重点实验室_多媒体计算
通讯作者	Yao, Hantao
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Sci & Technol China, Natl Engn Lab Brain Inspired Intelligence Technol, Hefei 230026, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
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	Yao, Hantao,Min, Shaobo,Zhang, Yongdong,et al. Attribute-Induced Bias Eliminating for Transductive Zero-Shot Learning[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2022,24:1933-1942.
APA	Yao, Hantao,Min, Shaobo,Zhang, Yongdong,&Xu, Changsheng.(2022).Attribute-Induced Bias Eliminating for Transductive Zero-Shot Learning.IEEE TRANSACTIONS ON MULTIMEDIA,24,1933-1942.
MLA	Yao, Hantao,et al."Attribute-Induced Bias Eliminating for Transductive Zero-Shot Learning".IEEE TRANSACTIONS ON MULTIMEDIA 24(2022):1933-1942.