Co-regularized Facial Age Estimation with Graph-Causal Learning

被引:0
作者
Wang, Tao [1 ]
Dong, Xin [1 ]
Li, Zhendong [1 ,2 ,3 ,4 ]
Liu, Hao [1 ,2 ,3 ,4 ]
机构
[1] Ningxia Univ, Sch Informat Engn, Yinchuan 750021, Ningxia, Peoples R China
[2] Collaborat Innovat Ctr Ningxia Big Data & Artific, Yinchuan 750021, Ningxia, Peoples R China
[3] Minist Educ, Yinchuan 750021, Ningxia, Peoples R China
[4] Key Lab Internet Water & Digital Water Governance, Yinchuan 750021, Ningxia, Peoples R China
来源
PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2023, PT VIII | 2024年 / 14432卷
基金
美国国家科学基金会;
关键词
Facial age estimation; Causal learning; Graph convolutional networks;
D O I
10.1007/978-981-99-8543-2_13
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we present a graph-causal regularization (GCR) for robust facial age estimation. Existing label facial age estimation methods often suffer from overfitting and overconfidence issues due to limited data and domain bias. To address these challenges and leveraging the chronological correlation of age labels, we propose a dynamic graph learning method that enforces causal regularization to discover an attentive feature space while preserving age label dependencies. To mitigate domain bias and enhance aging details, our approach incorporates counterfactual attention and bilateral pooling fusion techniques. Consequently, the proposed GCR achieves reliable feature learning and accurate ordinal decision-making within a globally-tuned framework. Extensive experiments under widely-used protocols demonstrate the superior performance of GCR compared to state-of-the-art approaches.
引用
收藏
页码:155 / 166
页数:12
相关论文
共 36 条
[1]   Face description with local binary patterns:: Application to face recognition [J].
Ahonen, Timo ;
Hadid, Abdenour ;
Pietikainen, Matti .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2006, 28 (12) :2037-2041
[2]   Divergence-Driven Consistency Training for Semi-Supervised Facial Age Estimation [J].
Bao, Zenghao ;
Tan, Zichang ;
Wan, Jun ;
Ma, Xibo ;
Guo, Guodong ;
Lei, Zhen .
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2023, 18 :221-232
[3]   New Graph Structured Sparsity Model for Multi-Label Image Annotations [J].
Cai, Xiao ;
Nie, Feiping ;
Cai, Weidong ;
Huang, Heng .
2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2013, :801-808
[4]   Facial age estimation using pre-trained CNN and transfer learning [J].
Dagher, Issam ;
Barbara, Dany .
MULTIMEDIA TOOLS AND APPLICATIONS, 2021, 80 (13) :20369-20380
[5]   PML: Progressive Margin Loss for Long-tailed Age Classification [J].
Deng, Zongyong ;
Liu, Hao ;
Wang, Yaoxing ;
Wang, Chenyang ;
Yu, Zekuan ;
Sun, Xuehong .
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, :10498-10507
[6]   ChaLearn Looking at People 2015: Apparent Age and Cultural Event Recognition datasets and results [J].
Escalera, Sergio ;
Fabian, Junior ;
Pardo, Pablo ;
Baro, Xavier ;
Gonzalez, Jordi ;
Escalante, Hugo J. ;
Misevic, Dusan ;
Steiner, Ulrich ;
Guyon, Isabelle .
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOP (ICCVW), 2015, :243-251
[7]   Age Synthesis and Estimation via Faces: A Survey [J].
Fu, Yun ;
Guo, Guodong ;
Huang, Thomas S. .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2010, 32 (11) :1955-1976
[8]  
Gao BB, 2018, PROCEEDINGS OF THE TWENTY-SEVENTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, P712
[9]   Label Distribution Learning [J].
Geng, Xin ;
Ji, Rongzi .
2013 IEEE 13TH INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS (ICDMW), 2013, :377-383
[10]   Facial Age Estimation by Learning from Label Distributions [J].
Geng, Xin ;
Yin, Chao ;
Zhou, Zhi-Hua .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2013, 35 (10) :2401-2412