Global Norm-Aware Pooling for Pose-Robust Face Recognition at Low False Positive Rate

TL;DR

This paper introduces a computationally efficient Global Norm-Aware Pooling (GNAP) block that adaptively reweights local features in CNNs, significantly improving pose-robust face recognition performance at low false positive rates.

Contribution

The paper presents a novel GNAP block that enhances face recognition by adaptively weighting features based on their norms, improving pose robustness without high computational costs.

Findings

GNAP reduces EER significantly in frontal-profile face recognition.

GNAP boosts TPR@FPR=0.1% substantially.

GNAP outperforms base models especially at low false positive rates.

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.