中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 智能感知与计算研究中心
Conditional High-Order Boltzmann Machines for Supervised Relation Learning

文献类型：期刊论文

作者Huang, Yan1,2; Wang, Wei1,2; Wang, Liang2,3,4; Tan, Tieniu2,3,4
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2017-09-01
卷号26期号:9页码:4297-4310
关键词Deep Learning High-order Boltzmann Machine Relation Learning Face Verification Action Similarity Labeling
DOI10.1109/TIP.2017.2698918
文献子类Article
英文摘要Relation 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.
WOS关键词DEEP NEURAL-NETWORK ; FACE VERIFICATION ; RECOGNITION ; DIMENSIONALITY ; ALGORITHM ; WILD
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000405395900004
资助机构National 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)
源URL[http://ir.ia.ac.cn/handle/173211/14821]  
专题自动化研究所_智能感知与计算研究中心
作者单位1.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
推荐引用方式
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.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。