Face recognition based on adaptive margin and diversity regularization constraints
Abstract In recent years, a more robust facial feature can be learned by convolutional neural networks once introducing margins into loss functions. Those methods set a margin for each class manually to squeeze the intra‐class variations within each class equally. However, the internal feature distr...
Main Authors: | Zhemin Zhang, Xun Gong, Junzhou Chen |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2021-04-01
|
Series: | IET Image Processing |
Online Access: | https://doi.org/10.1049/ipr2.12089 |
Similar Items
-
Efficient Face Recognition Using Regularized Adaptive Non-Local Sparse Coding
by: Masoud Alajmi, et al.
Published: (2019-01-01) -
Semisupervised Kernel Marginal Fisher Analysis for Face Recognition
by: Ziqiang Wang, et al.
Published: (2013-01-01) -
Regularized Deep Learning for Face Recognition With Weight Variations
by: Shruti Nagpal, et al.
Published: (2015-01-01) -
Block-Wise Two-Dimensional Maximum Margin Criterion for Face Recognition
by: Xiao-Zhang Liu, et al.
Published: (2014-01-01) -
Face Recognition Using Local Margin-Enhanced Classifier in Graph-Based Space
by: Shang-You Shi, et al.
Published: (2009)