Multi-Margin based Decorrelation Learning for Heterogeneous Face Recognition

TL;DR

This paper introduces a deep learning framework called Multi-Margin based Decorrelation Learning (MMDL) that effectively extracts decorrelation features for heterogeneous face recognition, improving verification and recognition accuracy across different domains.

Contribution

The paper proposes a novel deep neural network with a decorrelation layer and a multi-margin loss for enhanced cross-domain face recognition, outperforming existing methods.

Findings

Achieves superior performance on two challenging heterogeneous face datasets.

Outperforms state-of-the-art methods in verification and recognition tasks.

Effectively learns decorrelation representations in a hyperspherical space.

Abstract

Heterogeneous face recognition (HFR) refers to matching face images acquired from different domains with wide applications in security scenarios. This paper presents a deep neural network approach namely Multi-Margin based Decorrelation Learning (MMDL) to extract decorrelation representations in a hyperspherical space for cross-domain face images. The proposed framework can be divided into two components: heterogeneous representation network and decorrelation representation learning. First, we employ a large scale of accessible visual face images to train heterogeneous representation network. The decorrelation layer projects the output of the first component into decorrelation latent subspace and obtains decorrelation representation. In addition, we design a multi-margin loss (MML), which consists of quadruplet margin loss (QML) and heterogeneous angular margin loss (HAML), to constrain the proposed framework. Experimental results on two challenging heterogeneous face databases show that our approach achieves superior performance on both verification and recognition tasks, comparing with state-of-the-art methods.