Name
Title | ||
|---|---|---|
Unleash the Black Magic in Age: A Multi-Task Deep Neural Network Approach for Cross-Age Face Verification |
Abstract | ||
|---|---|---|
Facial aging is a complicated process which usually affects the facial appearance (e.g., wrinkles). Variations of facial appearance pose a big challenge to the automatic face recognition problem. How to eliminate the influence of aging factors to the verification performance is a very challenging problem. Multi-task learning has provided a principled framework for jointly learning multiple related tasks to improve generalization performance. In this paper, we leverage this powerful technique to improve the task of cross-age face verification. We present an end-to-end learning framework for cross-age face verification by designing a multi-task deep neural network architecture that exploits the intrinsic low-dimensional representation shared between the tasks of face verification and age estimation. We show that the algorithm effectively balances feature sharing and feature exclusion between the two given tasks. We evaluate the proposed framework on two standard benchmarks. Experimental results demonstrate that our algorithm has significant improvement over the state-of-theart (2.2% EER on MORPH and 7.8% EER on FG-NET, by more than 50.0% and 59.70% performance gain respectively). |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1109/FG.2017.75 | 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017) |
Keywords | Field | DocType |
multitask deep neural network,cross-age face verification,facial aging,facial appearance variations,automatic face recognition problem,aging factor elimination,multitask learning,multiple related task learning,generalization performance,end-to-end learning framework,intrinsic low-dimensional representation,age estimation,feature sharing,feature exclusion,MORPH,EER,FG-NET | Face verification,Facial recognition system,Computer science,Neural network architecture,Exploit,Artificial intelligence,Artificial neural network,Machine learning | Conference |
ISSN | ISBN | Citations |
2326-5396 | 978-1-5090-4024-7 | 4 |
PageRank | References | Authors |
0.65 | 40 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xiaolong Wang | 1 | 185 | 10.92 |
| Yin Zhou | 2 | 122 | 10.27 |
| Deguang Kong | 3 | 374 | 21.68 |
| Jon Currey | 4 | 961 | 60.12 |
| Dawei Li | 5 | 60 | 10.43 |
| Jiayu Zhou | 6 | 765 | 56.69 |