文献类型：期刊文献

英文题名：MMatch: Semi-Supervised Discriminative Representation Learning for Multi-View Classification

作者：Wang, Xiaoli[1] Fu, Liyong[2,3] Zhang, Yudong[4] Wang, Yongli[1] Li, Zechao[1]

第一作者：Wang, Xiaoli

通信作者：Fu, LY[1]

机构：[1]Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Nanjing 210000, Peoples R China;[2]Chinese Acad Forestry, Res Inst Forest Resource Informat Tech, Beijing 100091, Peoples R China;[3]Natl Forestry & Grassland Adm, Key Lab Forest Management & Growth Modeling, Beijing 100091, Peoples R China;[4]Henan Polytech Univ, Sch Comp Sci & Technol, Jiaozuo 454000, Henan, Peoples R China

年份：2022

卷号：32

期号：9

起止页码：6425-6436

外文期刊名：IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY

收录：;EI(收录号：20221211818397);Scopus(收录号：2-s2.0-85126528998);WOS:【SCI-EXPANDED(收录号:WOS:000849300000057)】；

基金：This work was supported in part by the 14th Five-Year Plan Pioneering Project of High Technology Plan of the National Department of Technology under Grant 2021YFD2200405, in part by the National Natural Science Foundation of China under Grant U20B2064 and Grant U21B2043, and in part by the Central Public Interest Scientific Institution Basal Research Fund under Grant CAFYBB2016SZ003. This article was recommended by Associate Editor S. Wang.

语种：英文

外文关键词：Representation learning; Training; Predictive models; Forestry; Feature extraction; Entropy; Task analysis; Semi-supervised learning; multi-view classification; discriminative representation; pseudo-labeling

摘要：Semi-supervised multi-view learning has been an important research topic due to its capability to exploit complementary information from unlabeled multi-view data. This work proposes MMatch, a new semi-supervised discriminative representation learning method for multi-view classification. Unlike existing multi-view representation learning methods that seldom consider the negative impact caused by particular views with unclear classification structures (weak discriminative views). MMatch jointly learns view-specific representations and class probabilities of training data. The representations concatenated to integrate multiple views' information to form a global representation. Moreover, MMatch performs the smoothness constraint on the class probabilities of the global representation to improve pseudo labels, whereas the pseudo labels regularize the structure of view-specific representations. A discriminative global representation is mined with the training process, and the negative impact of weak discriminative views is overcome. Besides, MMatch learns consistent classification while preserving diverse information from multiple views. Experiments on several multi-view datasets demonstrate the effectiveness of MMatch.