Meta Auxiliary Learning for Facial Action Unit Detection

被引:7
|
作者
Li, Yong [1 ,2 ]
Shan, Shiguang [3 ,4 ]
机构
[1] Nanjing Univ Sci & Technol, PCA Lab, Minist Educ, Key Lab Intelligent Percept & Syst High Dimens inf, Nanjing 210094, Peoples R China
[2] Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Jiangsu Key Lab Image & Video Understanding Social, Nanjing 210094, Peoples R China
[3] Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China
[4] CAS Ctr Excellencein Brain Sci & Intelligence Tech, Shanghai 200031, Peoples R China
基金
国家重点研发计划; 中国国家自然科学基金;
关键词
Facial action unit detection; auxiliary learning; meta learning; EXPRESSIONS;
D O I
10.1109/TAFFC.2021.3135516
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Despite the success of deep neural networks on facial action unit (AU) detection, better performance depends on a large number of training images with accurate AU annotations. However, labeling AU is time-consuming, expensive, and error-prone. Considering AU detection and facial expression recognition (FER) are two highly correlated tasks, and facial expression (FE) is relatively easy to annotate, we consider learning AU detection and FER in a multi-task manner. However, the performance of the AU detection task cannot be always enhanced due to the negative transfer in the multi-task scenario. To alleviate this issue, we propose a Meta Auxiliary Learning method (MAL) that automatically selects highly related FE samples by learning adaptative weights for the training FE samples in a meta learning manner. The learned sample weights alleviate the negative transfer from two aspects: 1) balance the loss of each task automatically, and 2) suppress the weights of FE samples that have large uncertainties. Experimental results on several popular AU datasets demonstrate MAL consistently improves the AU detection performance compared with the state-of-the-art multi-task and auxiliary learning methods. MAL automatically estimates adaptive weights for the auxiliary FE samples according to their semantic relevance with the primary AU detection task.
引用
收藏
页码:2526 / 2538
页数:13
相关论文
共 50 条
  • [1] Learning deep representation for action unit detection with auxiliary facial attributes
    Zhou, Caixia
    Zhi, Ruicong
    [J]. INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2022, 13 (02) : 407 - 419
  • [2] Learning deep representation for action unit detection with auxiliary facial attributes
    Caixia Zhou
    Ruicong Zhi
    [J]. International Journal of Machine Learning and Cybernetics, 2022, 13 : 407 - 419
  • [3] Semantic Learning for Facial Action Unit Detection
    Wang, Xuehan
    Chen, C. L. Philip
    Yuan, Haozhang
    Zhang, Tong
    [J]. IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS, 2023, 10 (03) : 1372 - 1380
  • [4] Learning to combine local models for Facial Action Unit detection
    Jaiswal, Shashank
    Martinez, Brais
    Valstar, Michel F.
    [J]. 2015 11TH IEEE INTERNATIONAL CONFERENCE AND WORKSHOPS ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG), VOL. 6, 2015,
  • [5] Facial Action Unit Detection Using Attention and Relation Learning
    Shao, Zhiwen
    Liu, Zhilei
    Cai, Jianfei
    Wu, Yunsheng
    Ma, Lizhuang
    [J]. IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, 2022, 13 (03) : 1274 - 1289
  • [6] On Multi-task Learning for Facial Action Unit Detection
    Zhang, Xiao
    Mahoor, Mohammad H.
    Nielsen, Rodney D.
    [J]. PROCEEDINGS OF 2013 28TH INTERNATIONAL CONFERENCE ON IMAGE AND VISION COMPUTING NEW ZEALAND (IVCNZ 2013), 2013, : 202 - 207
  • [7] Dual Learning for Facial Action Unit Detection Under Nonfull Annotation
    Wang, Shangfei
    Ding, Heyan
    Peng, Guozhu
    [J]. IEEE TRANSACTIONS ON CYBERNETICS, 2022, 52 (04) : 2225 - 2237
  • [8] Dual Learning for Joint Facial Landmark Detection and Action Unit Recognition
    Wang, Shangfei
    Chang, Yanan
    Wang, Can
    [J]. IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, 2023, 14 (02) : 1404 - 1416
  • [9] Emotion-aware Contrastive Learning for Facial Action Unit Detection
    Sun, Xuran
    Zeng, Jiabei
    Shan, Shiguang
    [J]. 2021 16TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2021), 2021,
  • [10] Facial Action Unit Detection With Transformers
    Jacob, Geethu Miriam
    Stenger, Bjorn
    [J]. 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 7676 - 7685