ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

MAN: Mining Ambiguity and Noise for Facial Expression Recognition in the Wild

Zhang, Ziyang; Sun, Xiao*; Li, Jia; Wang, Meng
PATTERN RECOGNITION LETTERS2022-12DOI: 10.1016/j.patrec.2022.10.016
3被引8阅读
引用收藏
分享

摘要

Due to the ambiguous expressions and the subjectiveness of annotators, annotation ambiguity is a seri-ous obstacle for facial expression recognition (FER). Ambiguous annotation exists in similar and dissimilar classes, which we call ambiguity and noise. The previous state-of-the-art approaches use uncertainty to generalize the two categories, and adopt uncertainty learning to suppress uncertainty samples. However, ambiguous expressions are confused with noisy label expressions may bias the model toward easy sam-ples and hurt the generalization capability. To solve this problem, we propose a novel approach to mine ambiguity and noise (MAN) in FER datasets. Specifically, we design a co-division module, which divides the datasets into clean, ambiguous and noisy label expressions based on the consistency and inconsis-tency between the predictions of two networks and the given labels. To effectively learn the clean ex-pressions, improve discriminative ability and avoid memorizing noisy labels, the tri-regularization module employs supervised learning, mutuality learning and unsupervised learning for the three subsets, respec-tively. Extensive experiments have shown that MAN can effectively mine the real ambiguity and noise, and achieve state-of-the-art performance in both synthetic noisy datasets and popular benchmarks.

学科与关键词

关键词
Facial Expression RecognitionAnnotation ambiguityMutual LearningUnsupervised Learning
相关
加载中…
  • Toward Facial Expression Recognition in the Wild via Noise-Tolerant Network
    Gu, Yu; Yan, Huan*; Zhang, Xiang; Wang, Yantong; Ji, Yusheng; Ren, FujiIEEE Transactions on Circuits and Systems for Video Technology, 2023, 33(5): 2033-2047.
  • Uncertain Label Correction via Auxiliary Action Unit Graphs for Facial Expression Recognition
    Liu, Yang; Zhang, Xingming; Kauttonen, Janne; Zhao, Guoying*26th International Conference on Pattern Recognition / 8th International Workshop on Image Mining - Theory and Applications (IMTA), Montreal, CANADA, 2022-08-21 To 2022-08-25.被引 3
  • Adaptive graph-based feature normalization for facial expression recognition
    Xiong, Yu-Jie*; Wang, Qingqing*; Du, Yangtao; Lu, YueENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2024, 129: 107623.
查看全部 →

发表信息

论文状态
公开发表
期刊
PATTERN RECOGNITION LETTERS
发表日期
2022-12
卷期
第 164 卷
页码
23-29
DOI
10.1016/j.patrec.2022.10.016
语言
ENGLISH
期刊等级
3区
成果收录
SCIE
资助标注
General Program of the National Natural Science Foundation of China [61976078]; National Key R&D Program of China [2019YFA0706203]; Anhui Provincial Natural Science Foundation [2208085QF191]; Fundamental Research Funds for the Central Universities [JZ2022HGTA0343]

作者

  • Z

    Zhang, Ziyang (第一作者)

  • S

    Sun, Xiao (通讯)

查看全部 4 位作者收起作者
  • L

    Li, Jia

  • W

    Wang, Meng

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417