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

Enhanced Hybrid Vision Transformer with Multi-Scale Feature Integration and Patch Dropping for Facial Expression Recognition

Li, Nianfeng; Huang, Yongyuan; Wang, Zhenyan; Fan, Ziyao; Li, Xinyuan; Xiao, Zhiguo*北京理工大学
SENSORS2024-7DOI: 10.3390/s24134153
2阅读
引用收藏
分享

摘要

Convolutional neural networks (CNNs) have made significant progress in the field of facial expression recognition (FER). However, due to challenges such as occlusion, lighting variations, and changes in head pose, facial expression recognition in real-world environments remains highly challenging. At the same time, methods solely based on CNN heavily rely on local spatial features, lack global information, and struggle to balance the relationship between computational complexity and recognition accuracy. Consequently, the CNN-based models still fall short in their ability to address FER adequately. To address these issues, we propose a lightweight facial expression recognition method based on a hybrid vision transformer. This method captures multi-scale facial features through an improved attention module, achieving richer feature integration, enhancing the network's perception of key facial expression regions, and improving feature extraction capabilities. Additionally, to further enhance the model's performance, we have designed the patch dropping (PD) module. This module aims to emulate the attention allocation mechanism of the human visual system for local features, guiding the network to focus on the most discriminative features, reducing the influence of irrelevant features, and intuitively lowering computational costs. Extensive experiments demonstrate that our approach significantly outperforms other methods, achieving an accuracy of 86.51% on RAF-DB and nearly 70% on FER2013, with a model size of only 3.64 MB. These results demonstrate that our method provides a new perspective for the field of facial expression recognition.

学科与关键词

关键词
facial expression recognitionlightweight networkattention moduletransformer
相关
加载中…
  • Facial Expression Recognition Based on Fine-Tuned Channel-Spatial Attention Transformer
    Yao, Huang; Yang, Xiaomeng; Chen, Di; Wang, Zhao; Tian, Yuan*SENSORS, 2023, 23(15): 6799.被引 1
  • Multiscale Feature Fusion Attention Lightweight Facial Expression Recognition
    Ni, Jinyuan; Zhang, Xinyue; Zhang, Jianxun*International Journal of Aerospace Engineering, 2022, 2022: 6523234.被引 2
  • A Cascade Attention Based Facial Expression Recognition Network by Fusing Multi-Scale Spatio-Temporal Features
    Zhu, Xiaoliang; He, Zili; Zhao, Liang*; Dai, Zhicheng*; Yang, QiaolaiSENSORS, 2022, 22(4): 1350.被引 11
查看全部 →

发表信息

论文状态
公开发表
期刊
SENSORS
发表日期
2024-07
卷期
第 24 卷, 第 13 期
页码
4153
DOI
10.3390/s24134153
语言
ENGLISH
成果收录
SCIE
资助标注
Jilin Provincial Science and Technology Development Program [20230401104YY, 20210201083GX]

作者

  • L

    Li, Nianfeng (第一作者)

    changchun univ

  • H

    Huang, Yongyuan

    changchun univ

查看全部 6 位作者收起作者
  • W

    Wang, Zhenyan

    changchun univ

  • F

    Fan, Ziyao

    changchun univ

  • L

    Li, Xinyuan

    changchun univ

  • X

    Xiao, Zhiguo (通讯)

    changchun univ · beijing inst technol

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