CASIA OpenIR  > 智能感知与计算研究中心
Conditional High-Order Boltzmann Machines for Supervised Relation Learning
Huang, Yan1,2; Wang, Wei1,2; Wang, Liang2,3,4; Tan, Tieniu2,3,4
Source PublicationIEEE TRANSACTIONS ON IMAGE PROCESSING
2017-09-01
Volume26Issue:9Pages:4297-4310
SubtypeArticle
AbstractRelation learning is a fundamental problem in many vision tasks. Recently, high-order Boltzmann machine and its variants have shown their great potentials in learning various types of data relation in a range of tasks. But most of these models are learned in an unsupervised way, i.e., without using relation class labels, which are not very discriminative for some challenging tasks, e.g., face verification. In this paper, with the goal to perform supervised relation learning, we introduce relation class labels into conventional high-order multiplicative interactions with pairwise input samples, and propose a conditional high-order Boltzmann Machine (CHBM), which can learn to classify the data relation in a binary classification way. To be able to deal with more complex data relation, we develop two improved variants of CHBM: 1) latent CHBM, which jointly performs relation feature learning and classification, by using a set of latent variables to block the pathway from pairwise input samples to output relation labels and 2) gated CHBM, which untangles factors of variation in data relation, by exploiting a set of latent variables to multiplicatively gate the classification of CHBM. To reduce the large number of model parameters generated by the multiplicative interactions, we approximately factorize high-order parameter tensors into multiple matrices. Then, we develop efficient supervised learning algorithms, by first pretraining the models using joint likelihood to provide good parameter initialization, and then finetuning them using conditional likelihood to enhance the discriminant ability. We apply the proposed models to a series of tasks including invariant recognition, face verification, and action similarity labeling. Experimental results demonstrate that by exploiting supervised relation labels, our models can greatly improve the performance.
KeywordDeep Learning High-order Boltzmann Machine Relation Learning Face Verification Action Similarity Labeling
WOS HeadingsScience & Technology ; Technology
DOI10.1109/TIP.2017.2698918
WOS KeywordDEEP NEURAL-NETWORK ; FACE VERIFICATION ; RECOGNITION ; DIMENSIONALITY ; ALGORITHM ; WILD
Indexed BySCI
Language英语
Funding OrganizationNational Key Research and Development Program of China(2016YFB1001000) ; National Natural Science Foundation of China(61525306 ; Strategic Priority Research Program of the CAS(XDB02070100) ; Beijing Natural Science Foundation(4162058) ; NVIDIA ; NVIDIA DGX-1 AI Supercomputer ; 61633021 ; 61572504 ; 61420106015)
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:000405395900004
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/14821
Collection智能感知与计算研究中心
Affiliation1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Ctr Res Intelligent Percept & Comp, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100044, Peoples R China
3.Chinese Acad Sci CASIA, Inst Automat, Natl Lab Pattern Recognit, Ctr Res Intelligent Percept & Comp, Beijing 100190, Peoples R China
4.CASIA, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Huang, Yan,Wang, Wei,Wang, Liang,et al. Conditional High-Order Boltzmann Machines for Supervised Relation Learning[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2017,26(9):4297-4310.
APA Huang, Yan,Wang, Wei,Wang, Liang,&Tan, Tieniu.(2017).Conditional High-Order Boltzmann Machines for Supervised Relation Learning.IEEE TRANSACTIONS ON IMAGE PROCESSING,26(9),4297-4310.
MLA Huang, Yan,et al."Conditional High-Order Boltzmann Machines for Supervised Relation Learning".IEEE TRANSACTIONS ON IMAGE PROCESSING 26.9(2017):4297-4310.
Files in This Item: Download All
File Name/Size DocType Version Access License
tip_final.pdf(4175KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Huang, Yan]'s Articles
[Wang, Wei]'s Articles
[Wang, Liang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Huang, Yan]'s Articles
[Wang, Wei]'s Articles
[Wang, Liang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Huang, Yan]'s Articles
[Wang, Wei]'s Articles
[Wang, Liang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: tip_final.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.