Graph Regularized Encoder-Decoder Networks for Image Representation Learning

doi:10.1109/TMM.2020.3020697

	Graph Regularized Encoder-Decoder Networks for Image Representation Learning
	Yang, Shijie 1,2; Li, Liang 3; Wang, Shuhui 3; Zhang, Weigang 4,5; Huang, Qingming 3; Tian, Qi 6
刊名	IEEE TRANSACTIONS ON MULTIMEDIA
	2021
卷号	23 页码:3124-3136
关键词	Laplace equations Visualization Manifolds Image reconstruction Task analysis Decoding Semantics Auto-encoder encoder-decoder graph regularizer image representation learning
ISSN号	1520-9210
DOI	10.1109/TMM.2020.3020697
英文摘要	Image representation learning with encoder-decoder networks plays a fundamental role in multimedia processing. Recent findings show that traditional encoder-decoders can be negatively affected by small visual perturbations. The learned non-smooth feature embedding cannot guarantee to capture semantic-meaningful geometric distance between visually-similar image samples. Inspired by manifold learning, we propose a graph regularized encoder-decoder network, which can preserve local geometric information of the code embedding space. More discriminative feature embedding is learnt to attain both high-level image semantic and neighbor relationship of image clusters. The proposed graph regularizer is formulated upon multi-layer perceptions. It uses the local invariance principle to explicitly reconstruct the geometric similarity graph. Theoretical analysis is provided to show the connection between our deep regularizer and traditional graph Laplacian regularizer. Practically, the network complexity is alleviated by anchor based bipartite graph, and this leverages our method into large scale scenario. Experimental evaluations show the comparable results of the proposed method with state-of-the-art models on different tasks.
资助项目	National Key R&D Program of China[2018YFE0303104] ; National Natural Science Foundation of China[61771457] ; National Natural Science Foundation of China[61732007] ; National Natural Science Foundation of China[61672497] ; National Natural Science Foundation of China[U1636214] ; National Natural Science Foundation of China[61931008] ; National Natural Science Foundation of China[61772494] ; National Natural Science Foundation of China[61836002] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-SYS013]
WOS研究方向	Computer Science ; Telecommunications
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000698902000014
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/17071]
专题	中国科学院计算技术研究所
通讯作者	Li, Liang
作者单位	1.Univ Chinese Acad Sci UCAS, Sch Comp Sci & Technol, Beijing 101408, Peoples R China 2.UCAS, Key Lab Big Data Min & Knowledge Management, Beijing 101408, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 4.Harbin Inst Technol, Sch Comp Sci & Technol, Weihai 264209, Peoples R China 5.Chinese Acad Sci, Univ Chinese Acad Sci, Beijing 100049, Peoples R China 6.Huawei Noahs Ark Lab, Hong Kong, Peoples R China
推荐引用方式 GB/T 7714	Yang, Shijie,Li, Liang,Wang, Shuhui,et al. Graph Regularized Encoder-Decoder Networks for Image Representation Learning[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2021,23:3124-3136.
APA	Yang, Shijie,Li, Liang,Wang, Shuhui,Zhang, Weigang,Huang, Qingming,&Tian, Qi.(2021).Graph Regularized Encoder-Decoder Networks for Image Representation Learning.IEEE TRANSACTIONS ON MULTIMEDIA,23,3124-3136.
MLA	Yang, Shijie,et al."Graph Regularized Encoder-Decoder Networks for Image Representation Learning".IEEE TRANSACTIONS ON MULTIMEDIA 23(2021):3124-3136.