%0 Generic %1 citeulike:14638047 %A xxx, %D 2018 %K arch metric pooling %T Global Norm-Aware Pooling for Pose-Robust Face Recognition at Low False Positive Rate %U http://arxiv.org/abs/1808.00435 %X In this paper, we propose a novel Global Norm-Aware Pooling (GNAP) block, which reweights local features in a convolutional neural network (CNN) adaptively according to their L2 norms and outputs a global feature vector with a global average pooling layer. Our GNAP block is designed to give dynamic weights to local features in different spatial positions without losing spatial symmetry. We use a GNAP block in a face feature embedding CNN to produce discriminative face feature vectors for pose-robust face recognition. The GNAP block is of very cheap computational cost, but it is very powerful for frontal-profile face recognition. Under the CFP frontal-profile protocol, the GNAP block can not only reduce EER dramatically but also boost TPR@FPR=0.1\% (TPR i.e. True Positive Rate, FPR i.e. False Positive Rate) substantially. Our experiments show that the GNAP block greatly promotes pose-robust face recognition over the base model especially at low false positive rate.

@misc{citeulike:14638047, abstract = {{In this paper, we propose a novel Global Norm-Aware Pooling (GNAP) block, which reweights local features in a convolutional neural network (CNN) adaptively according to their L2 norms and outputs a global feature vector with a global average pooling layer. Our GNAP block is designed to give dynamic weights to local features in different spatial positions without losing spatial symmetry. We use a GNAP block in a face feature embedding CNN to produce discriminative face feature vectors for pose-robust face recognition. The GNAP block is of very cheap computational cost, but it is very powerful for frontal-profile face recognition. Under the CFP frontal-profile protocol, the GNAP block can not only reduce EER dramatically but also boost TPR@FPR=0.1\% (TPR i.e. True Positive Rate, FPR i.e. False Positive Rate) substantially. Our experiments show that the GNAP block greatly promotes pose-robust face recognition over the base model especially at low false positive rate.}}, added-at = {2019-02-27T22:23:29.000+0100}, archiveprefix = {arXiv}, author = {xxx}, biburl = {https://www.bibsonomy.org/bibtex/2ed87910382fd694a942b10413cc40dbe/nmatsuk}, citeulike-article-id = {14638047}, citeulike-linkout-0 = {http://arxiv.org/abs/1808.00435}, citeulike-linkout-1 = {http://arxiv.org/pdf/1808.00435}, day = 1, eprint = {1808.00435}, interhash = {128af9b6a1abc04f165d9e6384ceed91}, intrahash = {ed87910382fd694a942b10413cc40dbe}, keywords = {arch metric pooling}, month = aug, posted-at = {2018-09-20 12:13:51}, priority = {5}, timestamp = {2019-02-27T22:23:29.000+0100}, title = {{Global Norm-Aware Pooling for Pose-Robust Face Recognition at Low False Positive Rate}}, url = {http://arxiv.org/abs/1808.00435}, year = 2018 }