中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Meta Auxiliary Learning for Facial Action Unit Detection

文献类型：期刊论文

作者Li, Yong2,3; Shan, Shiguang1,4
刊名IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
出版日期2023-07-01
卷号14期号:3页码:2526-2538
关键词Facial action unit detection auxiliary learning meta learning
ISSN号1949-3045
DOI10.1109/TAFFC.2021.3135516
英文摘要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.
资助项目National Key R&D Program of China ; Natural Science Foundation of Jiangsu Province[2017YFA0700800] ; National Natural Science Foundation of China[BK20210329] ; [62102180]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001075041900061
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/21125]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Shan, Shiguang
作者单位1.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China
2.Nanjing Univ Sci & Technol, PCA Lab, Minist Educ, Key Lab Intelligent Percept & Syst High Dimens inf, Nanjing 210094, Peoples R China
3.Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Jiangsu Key Lab Image & Video Understanding Social, Nanjing 210094, Peoples R China
4.CAS Ctr Excellencein Brain Sci & Intelligence Tech, Shanghai 200031, Peoples R China
推荐引用方式
GB/T 7714		 Li, Yong,Shan, Shiguang. Meta Auxiliary Learning for Facial Action Unit Detection[J]. IEEE TRANSACTIONS ON AFFECTIVE COMPUTING,2023,14(3):2526-2538.
APA Li, Yong,&Shan, Shiguang.(2023).Meta Auxiliary Learning for Facial Action Unit Detection.IEEE TRANSACTIONS ON AFFECTIVE COMPUTING,14(3),2526-2538.
MLA Li, Yong,et al."Meta Auxiliary Learning for Facial Action Unit Detection".IEEE TRANSACTIONS ON AFFECTIVE COMPUTING 14.3(2023):2526-2538.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。