基于动态卷积的标签不确定性自学习预测分配算法的面部表情识别  

Facial Expression Recognition Based on Self-Learning Label Prediction and Distribution Algorithm Based on Dynamic Convolutional for Label Uncertainty

作　　者：杨远奇[1] 蔡岱立 谢泽凌 江恩杰 YANG Yuanqi;CAI Daili;XIE Zeling;JIANG Enjie(Information Engineering,Chengyi College,Jimei University,Xiamen 361021,China;Shenzhen Hohem Technology Co.,Ltd.,Shenzhen 518071,China;Ningde Marine Center,MNR,Ningde 352100,China)

机构地区：[1]集美大学诚毅学院信息工程系,福建厦门361021 [2]深圳市浩瀚卓越科技有限公司,广东深圳518071 [3]自然资源部宁德海洋中心,福建宁德352100

出　　处：《集美大学学报(自然科学版)》2025年第2期186-197,共12页Journal of Jimei University:Natural Science

基　　金：中国高校产学研创新基金——新一代信息技术创新项目“基于SDN的车联网流量预测算法研究”(2021ITA06004);福建省中青年教师教育科研项目“车联网IoV流量预测算法研究”(JAT210671);集美大学诚毅学院中青年项目“基于transformer的推荐算法研究”(c13019)。

摘　　要：为解决在表情识别领域中数据集受到噪声、标注模糊、微表情等不确定性因素干扰的问题,提出了一种标签不确定性自学习预测分配算法。该算法包含三个核心模块:1)自注意力加权模块采用动态卷积实现精细的像素级注意力机制,有效降低计算负担;2)正则化排序模块通过样本权重排序和重新分配,优化了模型对不确定样本的处理;3)标签再分配模块对低权重样本进行标签校正,提高了整体预测精度。经过实验验证,该算法有效抑制了标签不确定性的影响,在RAF-DB和MMAFEDB等公开数据集上展现了卓越性能。To solve the problem of uncertain factors such as noise,fuzzy labeling,and micro expressions affecting the dataset in the field of facial expression recognition,a label uncertainty self-learning prediction allocation algorithm is proposed.The algorithm consists of three core modules:1)A self-attention weighting module employing dynamic convolution to achieve fine-grained pixel-level attention mechanism,effectively reducing computational overhead;2)A regularized ranking module that optimizes the model’s handling of uncertain samples through sample weight reranking and reallocation;3)A label reassignment module that corrects labels for low-weight samples,thereby improving overall prediction accuracy.Experimental validation demonstrates the algorithm’s efficacy in mitigating the impact of label uncertainty,exhibiting outstanding performance on publicly available datasets such as RAF-DB and MMAFEDB.

关 键 词：面部表情识别 标签不确定性自学习预测分配算法 动态卷积 抗噪神经网络 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]