An Exemplar-Based Multi-View Domain Generalization Framework for Visual Recognition

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.

I. Introduction

In the field of visual recognition, the data distributions of the training data and the testing data are usually quite different, in which the training set (resp., the testing set) is referred to as the source domain (resp., the target domain). Recently, abundant domain adaptation approaches [1]–[14] were proposed to reduce the data distribution mismatch between the source domain and the target domain explicitly. Nevertheless, the target domain samples are often unavailable during the training procedure and this problem is named domain generalization [15]. In comparison with domain adaptation, domain generalization aims to learn robust classifiers that can generalize well to arbitrary target domain. More recently, several domain generalization approaches [15]–[18] were also developed to enhance the generalization capability of the classifiers learnt on the source domain. For more details about domain generalization and adaptation, please refer to Section II.