当前位置: X-MOL 学术IEEE Trans. Cybern. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Deep Semisupervised Multiview Learning With Increasing Views
IEEE Transactions on Cybernetics ( IF 9.4 ) Pub Date : 2021-09-09 , DOI: 10.1109/tcyb.2021.3093626
Peng Hu 1 , Xi Peng 1 , Hongyuan Zhu 2 , Liangli Zhen 3 , Jie Lin 2 , Huaibai Yan 4 , Dezhong Peng 1
Affiliation  

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.

中文翻译:


增加视图的深度半监督多视图学习



在本文中,我们研究了半监督交叉视图学习中的两个具有挑战性的问题。一方面,大多数现有方法假设所有视图中的样本都具有成对关系,即需要在样本级别捕获或建立不同视图的对应关系。即使在半监督环境中,这样的假设也很容易被隔离,其中只有少数样本具有可用于建立对应关系的标签。另一方面,几乎所有现有的多视图方法,包括半监督方法,通常使用固定数据集来训练模型,这无法处理不断增加的视图数据。实际上,当部署新传感器时,视图数量将会增加。为了解决上述两个挑战,我们提出了一种新颖的方法,该方法采用多个独立的半监督特定视图网络(ISVN)以视图解耦的方式学习多个视图的表示。我们的方法有两个优点。由于我们专门设计的自动编码器和伪标签学习范例,我们的方法展示了一种利用标记和未标记数据的有效方法,同时放宽了成对关系(即对应关系)的数据假设。此外,通过我们的视图解耦策略,所提出的 ISVN 可以单独训练,从而有效地处理增加视图的数据,而无需重新训练整个模型。据我们所知,我们的 ISVN 可能是在半监督环境中处理增加的视图成为可能的首批尝试之一,也是非对应问题的有效解决方案。 为了验证我们方法的有效性和效率,我们通过比较 4 个多视图数据集上的 13 种最先进的方法在检索和分类方面进行了全面的实验。
更新日期:2021-09-09
down
wechat
bug