.png){kind=icon}
返回
Deep Semisupervised Multiview Learning With Increasing Views
.png){kind=icon}
PRE
AI
DOI：10.1109/TCYB.2021.3093626.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this article, we study two challenging problems in semisupervised cross-view learning. On the one hand, most existing methods assume that the samples in all views have a pairwise relationship, that is, it is necessary to capture or establish the correspondence of different views at the sample level. Such an assumption is easily isolated even in the semisupervised setting wherein only a few samples have labels that could be used to establish the correspondence. On the other hand, almost all existing multiview methods, including semisupervised ones, usually train a model using a fixed dataset, which cannot handle the data of increasing views. In practice, the view number will increase when new sensors are deployed. To address the above two challenges, we propose a novel method that employs multiple independent semisupervised view-specific networks (ISVNs) to learn representation for multiple views in a view-decoupling fashion. The advantages of our method are two-fold. Thanks to our specifically designed autoencoder and pseudolabel learning paradigm, our method shows an effective way to utilize both the labeled and unlabeled data while relaxing the data assumption of the pairwise relationship, that is, correspondence. Furthermore, with our view decoupling strategy, the proposed ISVNs could be separately trained, thus efficiently handling the data of increasing views without retraining the entire model. To the best of our knowledge, our ISVN could be one of the first attempts to make handling increasing views in the semisupervised setting possible, as well as an effective solution to the noncorresponding problem. To verify the effectiveness and efficiency of our method, we conduct comprehensive experiments by comparing 13 state-of-the-art approaches on four multiview datasets in terms of retrieval and classification.
Keyword:
Laplace equations
Data models
Training
Semantics
Correlation
Computer science
Space exploration
Cross-view retrieval
heterogeneous recognition
latent common space
semisupervised multiview learning
期刊
IF:
10.5
论文数:
1.1W
被引数:
5.0W
机构
引用论文
.png){kind=icon}
CCL: Cross-modal Correlation Learning With Multigrained Fusion by Hierarchical NetworkCCL: 分层网络多粒度融合的跨模态相关学习
OAAI
OAAI分享收藏
查看更多内容