This paper presents a new discriminative deep metric learning (DDML) method for face verification in the wild. Different from existing metric learning-based face verification methods which aim to learn a Mahalanobis distance metric to maximize the inter-class variations and minimize the intra-class variations, simultaneously, the proposed DDML trains a deep neural network which learns a set of hierarchical nonlinear transformations to project face pairs into the same feature subspace, under which the distance of each positive face pair is less than a smaller threshold and that of each negative pair is higher than a larger threshold, respectively, so that discriminative information can be exploited in the deep network. Our method achieves very competitive face verification performance on the widely used LFW and YouTube Faces (YTF) datasets.

This paper presents a new discriminative deep metric learning (DDML) method for face and kinship verification in wild conditions. While metric learning has achieved reasonably good performance in face and kinship verification, most existing metric learning methods aim to learn a single Mahalanobis distance metric to maximize the inter-class variations and minimize the intra-class variations, which cannot capture the nonlinear manifold where face images usually lie on. To address this, we propose a DDML method to train a deep neural network to learn a set of hierarchical nonlinear transformations to project face pairs into the same latent feature space, under which the distance of each positive pair is reduced and that of each negative pair is enlarged. To better use the commonality of multiple feature descriptors to make all the features more robust for face and kinship verification, we develop a discriminative deep multi-metric learning method to jointly learn multiple neural networks, under which the correlation of different features of each sample is maximized, and the distance of each positive pair is reduced and that of each negative pair is enlarged. Extensive experimental results show that our proposed methods achieve the acceptable results in both face and kinship verification.

Conventional metric learning methods usually assume that the training and test samples are captured in similar scenarios so that their distributions are assumed to be the same. This assumption doesn't hold in many real visual recognition applications, especially when samples are captured across different datasets. In this paper, we propose a new deep transfer metric learning (DTML) method to learn a set of hierarchical nonlinear transformations for cross-domain visual recognition by transferring discriminative knowledge from the labeled source domain to the unlabeled target domain. Specifically, our DTML learns a deep metric network by maximizing the inter-class variations and minimizing the intra-class variations, and minimizing the distribution divergence between the source domain and the target domain at the top layer of the network. To better exploit the discriminative information from the source domain, we further develop a deeply supervised transfer metric learning (DSTML) method by including an additional objective on DTML where the output of both the hidden layers and the top layer are optimized jointly. Experimental results on cross-dataset face verification and person re-identification validate the effectiveness of the proposed methods.

In this article, we have summarized the recent trends of DML and shown their wide applications of various visual understanding tasks including face recognition, image classification, visual search, person reidentification, visual tracking, cross-modal matching, and image set classification. Empirical results have clearly demonstrated that DML can significantly improve the state of the art in these visual understanding tasks.

This paper presents a sharable and individual multi-view metric learning (MvML) approach for visual recognition. Unlike conventional metric leaning methods which learn a distance metric on either a single type of feature representation or a concatenated representation of multiple types of features, the proposed MvML jointly learns an optimal combination of multiple distance metrics on multi-view representations, in which it not only learns an individual distance metric for each view to retain its specific property but also learns a shared representation for different views in a unified latent subspace to preserve their common properties. The objective function of the MvML is simply formulated in the large margin learning framework via pairwise constraints, under which the distance of each similar pair is smaller than that of each dissimilar pair by a margin. Moreover, to exploit the nonlinear structure of data points, we extend MvML to a sharable and individual multi-view deep metric learning (MvDML) method by utilizing the neural network architecture to seek multiple nonlinear transformations. Experimental results on face verification, kinship verification, and person re-identification show the effectiveness of the proposed sharable and individual multi-view metric learning methods.

In this paper, we present an automatic kinship verification system based on facial image analysis under uncontrolled conditions. While a large number of studies on human face analysis have been performed in the literature, there are a few attempts on automatic face analysis for kinship verification, possibly due to lacking of such publicly available databases and great challenges of this problem. To this end, we collect a kinship face database by searching 400+ pairs of public figures and celebrities from the internet, and automatically detect them with the Viola-Jones face detector. Then, we propose a new spatial pyramid learning-based (SPLE) feature descriptor for face representation and apply support vector machine (SVM) for kinship verification. The proposed system has the following three characteristics: 1) no manual human annotation of face landmarks is required and the kinship information is automatically obtained from the original pair of images; 2) both local appearance information and global spatial information have been effectively utilized in the proposed SPLE feature descriptor, and better performance can be obtained than state-of-the-art feature descriptors in our application; 3) the performance of our proposed system is comparable to that of human observers.