Paper Info
Title
Look Across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition.
Abstract
Despite the remarkable progress in face recognition related technologies, reliably recognizing faces across ages still remains a big challenge. The appearance of a human face changes substantially over time, resulting in significant intra-class variations. As opposed to current techniques for age-invariant face recognition, which either directly extract age-invariant features for recognition, or first synthesize a face that matches target age before feature extraction, we argue that it is more desirable to perform both tasks jointly so that they can leverage each other. To this end, we propose a deep Age-Invariant Model (AIM) for face recognition in the wild with three distinct novelties. First, AIM presents a novel unified deep architecture jointly performing cross-age face synthesis and recognition in a mutual boosting way. Second, AIM achieves continuous face rejuvenation/aging with remarkable photorealistic and identity-preserving properties, avoiding the requirement of paired data and the true age of testing samples. Third, we develop effective and novel training strategies for end-to-end learning the whole deep architecture, which generates powerful age-invariant face representations explicitly disentangled from the age variation. Moreover, we propose a new large-scale Cross-Age Face Recognition (CAFR) benchmark dataset to facilitate existing efforts and push the frontiers of age-invariant face recognition research. Extensive experiments on both our CAFR and several other cross-age datasets (MORPH, CACD and FG-NET) demonstrate the superiority of the proposed AIM model over the state-of-the-arts. Benchmarking our model on one of the most popular unconstrained face recognition datasets IJB-C additionally verifies the promising generalizability of AIM in recognizing faces in the wild.
Year
Venue
Field
2018
arXiv: Computer Vision and Pattern Recognition
Generalizability theory,Facial recognition system,Architecture,Pattern recognition,Computer science,Feature extraction,Invariant (mathematics),Artificial intelligence,Boosting (machine learning),Benchmarking,Feature learning,Machine learning
DocType
Volume
Citations 
Journal
abs/1809.00338
0
PageRank 
References 
Authors
0.34
32
15
Name
Order
Citations
PageRank
Jian Zhao1687.63
Yu Cheng261555.76
Yi Cheng313915.73
Yang Yang400.34
Haochong Lan500.34
Zhao, Fang6433.01
Lin Xiong7484.07
Xing Xu819927.30
Jianshu Li914112.04
Sugiri Pranata10365.78
Sheng Mei Shen1113113.13
Junliang Xing12119363.31
Hengzhu Liu138623.28
Shuicheng Yan1453937.48
Jiashi Feng152165140.81