DBLFace: Domain-Based Labels for NIR-VIS Heterogeneous Face Recognition

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Scopus citations

Abstract

Deep learning-based domain-invariant feature learning methods are advancing in near-infrared and visible (NIR-VIS) heterogeneous face recognition. However, these methods are prone to overfitting due to the large intra-class variation and the lack of NIR images for training. In this paper, we introduce Domain-Based Label Face (DBLFace), a learning approach based on the assumption that a subject is not represented by a single label but by a set of labels. Each label represents images of a specific domain. In particular, a set of two labels per subject, one for the NIR images and one for the VIS images, are used for training a NIR-VIS face recognition model. The classification of images into different domains reduces the intra-class variation and lessens the negative impact of data imbalance in training. To train a network with sets of labels, we introduce a domain-based angular margin loss and a maximum angular loss to maintain the inter-class discrepancy and to enforce the close relationship of labels in a set. Quantitative experiments confirm that DBLFace significantly improves the rank-1 identification rate by 6.7% on the EDGE20 dataset and achieves state-of-the-art performance on the CASIA NIR-VIS 2.0 dataset.

Original languageEnglish (US)
Title of host publicationIJCB 2020 - IEEE/IAPR International Joint Conference on Biometrics
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728191867
DOIs
StatePublished - Sep 28 2020
Event2020 IEEE/IAPR International Joint Conference on Biometrics, IJCB 2020 - Virtual, Online, United States
Duration: Sep 28 2020Oct 1 2020

Publication series

NameIJCB 2020 - IEEE/IAPR International Joint Conference on Biometrics

Conference

Conference2020 IEEE/IAPR International Joint Conference on Biometrics, IJCB 2020
Country/TerritoryUnited States
CityVirtual, Online
Period9/28/2010/1/20

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Biomedical Engineering
  • Instrumentation

Fingerprint

Dive into the research topics of 'DBLFace: Domain-Based Labels for NIR-VIS Heterogeneous Face Recognition'. Together they form a unique fingerprint.

Cite this