Relational Deep Feature Learning for Heterogeneous Face Recognition

Abstract

Heterogeneous Face Recognition (HFR) is a task that matches faces across two different domains such as visible light (VIS), near-infrared (NIR), or the sketch domain. Due to the lack of databases, HFR methods usually exploit the pre-trained features on a large-scale visual database that contain general facial information. However, these pre-trained features cause performance degradation due to the texture discrepancy with the visual domain. With this motivation, we propose a graph-structured module called Relational Graph Module (RGM) that extracts global relational information in addition to general facial features. Because each identity's relational information between intra-facial parts is similar in any modality, the modeling relationship between features can help cross-domain matching. Through the RGM, relation propagation diminishes texture dependency without losing its advantages from the pre-trained features. Furthermore, the RGM captures global facial geometrics from locally correlated convolutional features to identify long-range relationships. In addition, we propose a Node Attention Unit (NAU) that performs node-wise recalibration to concentrate on the more informative nodes arising from relation-based propagation. Furthermore, we suggest a novel conditional-margin loss function (C-softmax) for the efficient projection learning of the embedding vector in HFR. The proposed method outperforms other state-of-the-art methods on five HFR databases. Furthermore, we demonstrate performance improvement on three backbones because our module can be plugged into any pre-trained face recognition backbone to overcome the limitations of a small HFR database.

References in corpus (11)

• FaceNet: A Unified Embedding for Face Recognition and Clustering
• Semi-Supervised Classification with Graph Convolutional Networks
• Squeeze-and-Excitation Networks
• Learning Face Representation from Scratch
• Graph Neural Networks: A Review of Methods and Applications
• Deep Face Recognition: A Survey
• NormFace: L2 Hypersphere Embedding for Face Verification
• L2-constrained Softmax Loss for Discriminative Face Verification
• Deep Perceptual Mapping for Thermal to Visible Face Recognition
• Adversarial Discriminative Heterogeneous Face Recognition
• Disentangled Variational Representation for Heterogeneous Face Recognition

Cited by in corpus (5)

• Heterogeneous Face Recognition via Face Synthesis with Identity-Attribute Disentanglement
• Joint Feature Distribution Alignment Learning for NIR-VIS and VIS-VIS Face Recognition
• Heterogeneous Visible-Thermal and Visible-Infrared Face Recognition using Unit-Class Loss and Cross-Modality Discriminator
• A NIR-to-VIS face recognition via part adaptive and relation attention module
• DBLFace: Domain-Based Labels for NIR-VIS Heterogeneous Face Recognition