AAFACE: Attribute-aware Attentional Network for Face Recognition

TL;DR

This paper introduces AAFace, a multi-branch neural network that leverages soft biometric attributes through an attribute-aware attention mechanism to improve face recognition accuracy.

Contribution

The paper proposes a novel attribute-aware attentional integration module that enhances face recognition by effectively combining soft biometric features.

Findings

Outperforms state-of-the-art SB prediction methods

Achieves superior face recognition accuracy

Demonstrates effective integration of soft biometric attributes

Abstract

In this paper, we present a new multi-branch neural network that simultaneously performs soft biometric (SB) prediction as an auxiliary modality and face recognition (FR) as the main task. Our proposed network named AAFace utilizes SB attributes to enhance the discriminative ability of FR representation. To achieve this goal, we propose an attribute-aware attentional integration (AAI) module to perform weighted integration of FR with SB feature maps. Our proposed AAI module is not only fully context-aware but also capable of learning complex relationships between input features by means of the sequential multi-scale channel and spatial sub-modules. Experimental results verify the superiority of our proposed network compared with the state-of-the-art (SoTA) SB prediction and FR methods.