Paper Info
Title
The identity-level angular triplet loss for cross-age face recognition
Abstract
Despite promising progress has been achieved on face recognition problems, cross-age face recognition remains a challenging task due to its age variations. Human appearances change along with the age growing process, which increases the difficulty of recognition tasks. Existing methods mainly focus on synthesizing new facial images according to different age levels or isolating age-related features and identity related features. In this paper, we propose an identity-level angular triplet loss for cross-age face recognition. The facial images are projected to an embedding space where the angle between feature embeddings can represent similarities of images. Different from Euclidean distance metric, the angular metric used in our method guides the model to learn discriminative features under large intra-class discrepancy. Angles between intra-class embeddings are reduced while that between inter-class are enlarged. The selection of good triplets is conducted on an identity-level rather than instance-level with a moderate positive mining strategy. Experiments are conducted on cross-age databases and results prove the effectiveness of our method.
Year
DOI
Venue
2022
10.1007/s10489-021-02742-3
Applied Intelligence
Keywords
DocType
Volume
Cross-age face recognition, Angular embedding, Triplet loss, Metric learning
Journal
52
Issue
ISSN
Citations 
6
0924-669X
0
PageRank 
References 
Authors
0.34
15
2
Name
Order
Citations
PageRank
Xiaoyu Chen100.34
Henry Y. K. Lau216431.98