Joint Bayesian guided metric learning for end-to-end face verification

2018 ◽  
Vol 275 ◽  
pp. 560-567 ◽  
Author(s):  
Di Chen ◽  
Chunyan Xu ◽  
Jian Yang ◽  
Jianjun Qian ◽  
Yuhui Zheng ◽  
...  
Keyword(s):  
Metric Learning ◽  
Face Verification ◽  
End To End

FaceLiveNet: End-to-End Networks Combining Face Verification with Interactive Facial Expression-Based Liveness Detection

2018 ◽  
Author(s):  
Zuheng Ming ◽  
Joseph Chazalon ◽  
Muhammad Muzzamil Luqman ◽  
Muriel Visani ◽  
Jean-Christophe Burie
Keyword(s):  
Facial Expression ◽  
Face Verification ◽  
Liveness Detection ◽  
End To End

End-to-End Illuminant Estimation Based on Deep Metric Learning

2020 ◽  
Author(s):  
Bolei Xu ◽  
Jingxin Liu ◽  
Xianxu Hou ◽  
Bozhi Liu ◽  
Guoping Qiu
Keyword(s):  
Metric Learning ◽  
Illuminant Estimation ◽  
Deep Metric Learning ◽  
End To End

ECML: An Ensemble Cascade Metric-Learning Mechanism Toward Face Verification

2020 ◽  
pp. 1-14 ◽  
Author(s):  
Fu Xiong ◽  
Yang Xiao ◽  
Zhiguo Cao ◽  
Yancheng Wang ◽  
Joey Tianyi Zhou ◽  
...  
Keyword(s):  
Metric Learning ◽  
Face Verification ◽  
Learning Mechanism

scholarly journals Pairwise Ranking Distillation for Deep Face Recognition

2020 ◽  
pp. paper30-1-paper30-13
Author(s):  
Mikhail Nikitin ◽  
Vadim Konushin ◽  
Anton Konushin
Keyword(s):  
Face Recognition ◽  
Metric Learning ◽  
High Capacity ◽  
Recognition Task ◽  
Learning Task ◽  
Face Verification ◽  
Baseline Method ◽  
Task Knowledge ◽  
Model Compression ◽  
Knowledge Distillation

This work addresses the problem of knowledge distillation for deep face recognition task. Knowledge distillation technique is known to be an effective way of model compression, which implies transferring of the knowledge from high-capacity teacher to a lightweight student. The knowledge and the way how it is distilled can be defined in different ways depending on the problem where the technique is applied. Considering the fact that face recognition is a typical metric learning task, we propose to perform knowledge distillation on a score-level. Specifically, for any pair of matching scores computed by teacher, our method forces student to have the same order for the corresponding matching scores. We evaluate proposed pairwise ranking distillation (PWR) approach using several face recognition benchmarks for both face verification and face identification scenarios. Experimental results show that PWR not only can improve over the baseline method by a large margin, but also outperforms other score-level distillation approaches.

Weighted similarity and distance metric learning for unconstrained face verification with 3D frontalisation

2019 ◽  
Vol 13 (2) ◽  
pp. 399-408 ◽  
Author(s):  
Xin Xu ◽  
Jiuzhen Liang ◽  
Chen Chen ◽  
Zhenjie Hou
Keyword(s):  
Metric Learning ◽  
Face Verification ◽  
Distance Metric Learning ◽  
Distance Metric ◽  
Unconstrained Face

scholarly journals Multiview discriminative marginal metric learning for makeup face verification

2019 ◽  
Vol 333 ◽  
pp. 339-350 ◽  
Author(s):  
Lining Zhang ◽  
Hubert P. H. Shum ◽  
Li Liu ◽  
Guodong Guo ◽  
Ling Shao
Keyword(s):  
Metric Learning ◽  
Face Verification

scholarly journals A Novel Approach to Face Verification Based on Second-Order Face-Pair Representation

Complexity ◽  
2018 ◽  
Vol 2018 ◽  
pp. 1-10 ◽  
Author(s):  
Qiang Hua ◽  
Chunru Dong ◽  
Feng Zhang
Keyword(s):  
Binary Classification ◽  
Metric Learning ◽  
Second Order ◽  
Classification Model ◽  
Face Verification ◽  
Unified Framework ◽  
Face Pair ◽  
Face Representation ◽  
Representation Method ◽  
Pair Representation

Face representation and matching are two essential issues in face verification task. Various approaches have been proposed focusing on these two issues. However, few of them addressed the joint optimal solutions of these two issues in a unified framework. In this paper, we present a second-order face representation method for face pair and a unified face verification framework, in which the feature extractors and the subsequent binary classification model design can be selected flexibly. Our contributions can be summarized in the following aspects. First, a novel face-pair representation method that employs the second-order statistical property of the face pairs is proposed, which retains more information compared to the existing methods. Second, a flexible binary classification model, which differs from the conventionally used metric learning, is constructed based on the new face-pair representation. Finally, we verify that our proposed face-pair representation can benefit from large training datasets. All the experiments are carried out on Labeled Face in the Wild (LFW) to verify the algorithm’s effectiveness against challenging uncontrolled conditions.

Sign in / Sign up

Export Citation Format

Share Document