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 D-DML trains a deep neural network which learns a set of hierarchical nonlinear transformations to project face pairsinto 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.
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 crossdomain 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.
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.
To achieve sustainable development, focal firms should balance two paradoxical kinds of innovation activities: exploitative and exploratory ones. Published works found that ambidexterity is an effective way to resolve paradoxical tensions, but few in-depth studies have been conducted to explore the innovation paradox of focal firms in the innovation ecosystem from an ambidextrous capability perspective. This paper takes China Spacesat Co., Ltd. as the case to study focal firms' management of innovation paradoxes in the sustainable innovation ecosystem and finds that: (1) Sustainable innovation is an ecosystem in which focal firms' internal functional departments, including the product department, technical center, and Makers' groups, cooperate with external organizations, including component suppliers, scientific research institutes, and government departments, closely and complementarily; (2) In the exploitative and exploratory innovations of complex products, focal firms in the sustainable innovation ecosystem mainly confront three paradoxes: profit drive vs. breakthroughs in the strategic intent of sustainable innovation of the profit-driven model, tight vs. loose coupling of sustainable innovation, and sustainable innovation driven by discipline vs. that by passion; (3) Focal firms in the innovation ecosystem resolve these three innovation paradoxes with structural, contextual, and coordinated ambidextrous capabilities, and build innovation paradox management mechanisms with three steps in sequence, namely by establishing dual sustainable strategic innovation units, strengthening sustainable organizational ties between the internal and external, while co-creating and sharing innovation values, and, finally, promoting the formation and development of their sustainable innovation ecosystem. This paper complements and enriches the innovation ecosystem and ambidextrous capability theory, providing significant practical guidance to the sustainable development of aerospace enterprises.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.