LARNet: Lie Algebra Residual Network for Face Recognition

TL;DR

This paper introduces LARNet, a novel face recognition model leveraging Lie algebra theory to model how 3D face rotations affect CNN features, improving robustness to pose variations.

Contribution

The paper presents a theoretical link between face rotation and residual components in CNN features, leading to a new Lie Algebraic Residual Network for pose-invariant face recognition.

Findings

LARNet outperforms state-of-the-art methods on multiple face recognition datasets.

Theoretical proof links face rotation to additive residuals in CNN feature space.

Experimental results demonstrate improved robustness to pose variations.

Abstract

Face recognition is an important yet challenging problem in computer vision. A major challenge in practical face recognition applications lies in significant variations between profile and frontal faces. Traditional techniques address this challenge either by synthesizing frontal faces or by pose invariant learning. In this paper, we propose a novel method with Lie algebra theory to explore how face rotation in the 3D space affects the deep feature generation process of convolutional neural networks (CNNs). We prove that face rotation in the image space is equivalent to an additive residual component in the feature space of CNNs, which is determined solely by the rotation. Based on this theoretical finding, we further design a Lie Algebraic Residual Network (LARNet) for tackling pose robust face recognition. Our LARNet consists of a residual subnet for decoding rotation information from input face images, and a gating subnet to learn rotation magnitude for controlling the strength of the residual component contributing to the feature learning process. Comprehensive experimental evaluations on both frontal-profile face datasets and general face recognition datasets convincingly demonstrate that our method consistently outperforms the state-of-the-art ones.