Decorrelated Adversarial Learning for Age-Invariant Face Recognition

There has been an increasing research interest in age-invariant face recognition. However, matching faces with big age gaps remains a challenging problem, primarily due to the significant discrepancy of face appearance caused by aging. To reduce such discrepancy, in this paper we present a novel alg...

Full description

Saved in:
Bibliographic Details
Published in2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 3522 - 3531
Main Authors Wang, Hao, Gong, Dihong, Li, Zhifeng, Liu, Wei
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2019
Subjects
Aging
and Body Pose
Benchmark testing
Categorization
Computational modeling
Computer vision
Correlation
Deep learning
Face
Face recognition
Gesture
Recognition: Detection
Representation Learning
Retrieval
Online AccessGet full text

Cover

More Information
Summary:There has been an increasing research interest in age-invariant face recognition. However, matching faces with big age gaps remains a challenging problem, primarily due to the significant discrepancy of face appearance caused by aging. To reduce such discrepancy, in this paper we present a novel algorithm to remove age-related components from features mixed with both identity and age information. Specifically, we factorize a mixed face feature into two uncorrelated components: identity-dependent component and age-dependent component, where the identity-dependent component contains information that is useful for face recognition. To implement this idea, we propose the Decorrelated Adversarial Learning (DAL) algorithm, where a Canonical Mapping Module (CMM) is introduced to find maximum correlation of the paired features generated by the backbone network, while the backbone network and the factorization module are trained to generate features reducing the correlation. Thus, the proposed model learns the decomposed features of age and identity whose correlation is significantly reduced. Simultaneously, the identity-dependent feature and the age-dependent feature are supervised by ID and age preserving signals respectively to ensure they contain the correct information. Extensive experiments have been conducted on the popular public-domain face aging datasets (FG-NET, MORPH Album 2, and CACD-VS) to demonstrate the effectiveness of the proposed approach.
ISSN:2575-7075
DOI:10.1109/CVPR.2019.00364