Abstract
Learning large-margin face features whose intra-class variance is small and inter-class diversity is one of important challenges in feature learning applying Deep Convolutional Neural Networks (DCNNs) for face recognition. Recently, an appealing line of research is to incorporate an angular margin in the original softmax loss functions for obtaining discriminative deep features during the training of DCNNs. In this paper we propose a novel loss function, termed as double additive margin Softmax loss (DAM-Softmax). The presented loss has a clearer geometrical explanation and can obtain highly discriminative features for face recognition. Extensive experimental evaluation of several recent state-of-the-art softmax loss functions are conducted on the relevant face recognition benchmarks, CASIA-Webface, LFW, CALFW, CPLFW, and CFP-FP. We show that the proposed loss function consistently outperforms the state-of-the-art.
Highlights
Face recogniton problems are ubiquitous in the computer vision domain
Due to effectively layered end-to-end learning network frameworks and carefully deep feature extracting techniques from local to global, which are the most important ingredients for their success, Deep Convolutional Neural Networks (DCNNs) has immensely improved the state of the art in real-world face recognition scenarios
Due to the fact that few existing softmax losses can effectively achieve the discriminative condition that the maximal within-class variance is less than the minimal between-class variance under the conventional Euclidean metric space, more recently, approaches have been proposed to address this problem by transforming the original Euclidean space of features to an corresponding angular space [10,13,14,15]
Summary
Face recogniton problems are ubiquitous in the computer vision domain. In the past few years, Deep Convolutional Neural Networks (DCNNs) have set the community of face recognition (FR). Due to the fact that few existing softmax losses can effectively achieve the discriminative condition that the maximal within-class variance is less than the minimal between-class variance under the conventional Euclidean metric space, more recently, approaches have been proposed to address this problem by transforming the original Euclidean space of features to an corresponding angular space [10,13,14,15]. Both Large-Margin Softmax Loss [13] and A-Softmax Loss [14] are an angular softmax loss that enables DCNNs to learn angular deep features by imposing an angular margin constraint for larger inter-class variance.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
