Domain-invariant Face Recognition using Learned Low-rank Transformation

TL;DR

This paper introduces a low-rank transformation method that enhances face recognition across different domains by learning discriminative linear transformations to reduce intra-class variations and increase inter-class separations.

Contribution

It proposes a novel low-rank transformation approach that learns linear transformations to improve domain-invariant face recognition, addressing variations like pose and illumination.

Findings

Effective in reducing domain-induced face variations

Improves face recognition accuracy across different visual domains

Applicable to feature extraction in generic object recognition

Abstract

We present a low-rank transformation approach to compensate for face variations due to changes in visual domains, such as pose and illumination. The key idea is to learn discriminative linear transformations for face images using matrix rank as the optimization criteria. The learned linear transformations restore a shared low-rank structure for faces from the same subject, and, at the same time, force a high-rank structure for faces from different subjects. In this way, among the transformed faces, we reduce variations caused by domain changes within the classes, and increase separations between the classes for better face recognition across domains. Extensive experiments using public datasets are presented to demonstrate the effectiveness of our approach for face recognition across domains. The potential of the approach for feature extraction in generic object recognition and coded aperture design are discussed as well.