IEEE Trans Neural Netw Learn Syst. 2018 Feb;29(2):259-272. doi: 10.1109/TNNLS.2016.2615469. Epub 2016 Nov 3.
In this paper, we propose a new exemplar-based multi-view domain generalization (EMVDG) framework for visual recognition by learning robust classifier that are able to generalize well to arbitrary target domain based on the training samples with multiple types of features (i.e., multi-view features). In this framework, we aim to address two issues simultaneously. First, the distribution of training samples (i.e., the source domain) is often considerably different from that of testing samples (i.e., the target domain), so the performance of the classifiers learnt on the source domain may drop significantly on the target domain. Moreover, the testing data are often unseen during the training procedure. Second, when the training data are associated with multi-view features, the recognition performance can be further improved by exploiting the relation among multiple types of features. To address the first issue, considering that it has been shown that fusing multiple SVM classifiers can enhance the domain generalization ability, we build our EMVDG framework upon exemplar SVMs (ESVMs), in which a set of ESVM classifiers are learnt with each one trained based on one positive training sample and all the negative training samples. When the source domain contains multiple latent domains, the learnt ESVM classifiers are expected to be grouped into multiple clusters. To address the second issue, we propose two approaches under the EMVDG framework based on the consensus principle and the complementary principle, respectively. Specifically, we propose an EMVDG_CO method by adding a co-regularizer to enforce the cluster structures of ESVM classifiers on different views to be consistent based on the consensus principle. Inspired by multiple kernel learning, we also propose another EMVDG_MK method by fusing the ESVM classifiers from different views based on the complementary principle. In addition, we further extend our EMVDG framework to exemplar-based multi-view domain adaptation (EMVDA) framework when the unlabeled target domain data are available during the training procedure. The effectiveness of our EMVDG and EMVDA frameworks for visual recognition is clearly demonstrated by comprehensive experiments on three benchmark data sets.
在本文中，我们提出了一种新的基于示例的多视图域泛化（EMVDG）框架，用于视觉识别，通过学习基于具有多种类型特征（即多视图特征）的训练样本的稳健分类器，该分类器能够很好地推广到任意目标域。在这个框架中，我们旨在同时解决两个问题。首先，训练样本的分布（即源域）通常与测试样本（即目标域）有很大的不同，因此在源域上学习的分类器在目标域上的性能可能会显著下降。此外，在训练过程中，测试数据通常是不可见的。其次，当训练数据与多视图特征相关联时，通过利用多种类型特征之间的关系，可以进一步提高识别性能。为了解决第一个问题，考虑到融合多个 SVM 分类器可以增强域泛化能力，我们在示例 SVM（ESVM）的基础上构建了我们的 EMVDG 框架，其中一组 ESVM 分类器是通过对每个分类器进行训练而得到的，每个分类器都基于一个正训练样本和所有负训练样本进行训练。当源域包含多个潜在域时，所学习的 ESVM 分类器预计将被分组到多个聚类中。为了解决第二个问题，我们在 EMVDG 框架下提出了两种基于一致性原则和互补性原则的方法。具体来说，我们通过添加一个协同正则化项来强制 ESVM 分类器在不同视图上的聚类结构基于一致性原则保持一致，提出了 EMVDG_CO 方法。受多核学习的启发，我们还提出了另一种 EMVDG_MK 方法，通过基于互补性原则融合来自不同视图的 ESVM 分类器。此外，当在训练过程中可用未标记的目标域数据时，我们还将我们的 EMVDG 框架进一步扩展到基于示例的多视图域自适应（EMVDA）框架。在三个基准数据集上的综合实验清楚地证明了我们的 EMVDG 和 EMVDA 框架在视觉识别中的有效性。
