arXiv Analytics

Sign in

arXiv:2007.05720 [cs.CV]AbstractReferencesReviewsResources

ECML: An Ensemble Cascade Metric Learning Mechanism towards Face Verification

Fu Xiong, Yang Xiao, Zhiguo Cao, Yancheng Wang, Joey Tianyi Zhou, Jianxi Wu

Published 2020-07-11Version 1

Face verification can be regarded as a 2-class fine-grained visual recognition problem. Enhancing the feature's discriminative power is one of the key problems to improve its performance. Metric learning technology is often applied to address this need, while achieving a good tradeoff between underfitting and overfitting plays the vital role in metric learning. Hence, we propose a novel ensemble cascade metric learning (ECML) mechanism. In particular, hierarchical metric learning is executed in the cascade way to alleviate underfitting. Meanwhile, at each learning level, the features are split into non-overlapping groups. Then, metric learning is executed among the feature groups in the ensemble manner to resist overfitting. Considering the feature distribution characteristics of faces, a robust Mahalanobis metric learning method (RMML) with closed-form solution is additionally proposed. It can avoid the computation failure issue on inverse matrix faced by some well-known metric learning approaches (e.g., KISSME). Embedding RMML into the proposed ECML mechanism, our metric learning paradigm (EC-RMML) can run in the one-pass learning manner. Experimental results demonstrate that EC-RMML is superior to state-of-the-art metric learning methods for face verification. And, the proposed ensemble cascade metric learning mechanism is also applicable to other metric learning approaches.

Comments: Accepted to IEEE Transaction on Cybernetics
Categories: cs.CV
Related articles: Most relevant | Search more
arXiv:1401.6108 [cs.CV] (Published 2013-11-19)
Face Verification Using Kernel Principle Component Analysis
arXiv:1603.03958 [cs.CV] (Published 2016-03-12)
Template Adaptation for Face Verification and Identification
arXiv:2001.07323 [cs.CV] (Published 2020-01-21)
Face Verification via learning the kernel matrix