# Multi-Margin based Decorrelation Learning for Heterogeneous Face Recognition

arXiv: https://arxiv.org/abs/2005.11945 · HTML: https://mlsanity.com/paper/2005.11945/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2020.

## Built on by (most cited first, 5 of 5)

- [Beyond the Visible: A Survey on Cross-spectral Face Recognition](https://mlsanity.com/paper/2201.04435/) (2022)
- [Unconstrained Face Sketch Synthesis via Perception-Adaptive Network and A New Benchmark](https://mlsanity.com/paper/2112.01019/) (2021)
- [Joint Feature Distribution Alignment Learning for NIR-VIS and VIS-VIS Face Recognition](https://mlsanity.com/paper/2204.11434/) (2022)
- [Reliability Check via Weight Similarity in Privacy-Preserving Multi-Party Machine Learning](https://mlsanity.com/paper/2101.05504/) (2021)
- [MoDE: Mixture of Diffusion Experts for Any Occluded Face Recognition](https://mlsanity.com/paper/2505.04306/) (2025)

## Abstract (arXiv)

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.