Abstract
Facial expression recognition (FER) plays a significant role in our daily life. However, annotation ambiguity in the datasets could greatly hinder the performance. In this paper, we address FER task via label distribution learning paradigm, and develop a dual-branch Adaptive Distribution Fusion (Ada-DF) framework. One auxiliary branch is constructed to obtain the label distributions of samples. The class distributions of emotions are then computed through the label distributions of each emotion. Finally, those two distributions are adaptively fused according to the attention weights to train the target branch. Extensive experiments are conducted on three real-world datasets, RAF-DB, AffectNet and SFEW, where our Ada-DF shows advantages over the state-of-the-art works.
Abstract (translated)
面部表情识别(FER)在我们的日常生活中扮演着重要的角色。然而,数据集中注释的不明确性可能极大地阻碍了性能。在本文中,我们通过标签分布学习范式来解决FER任务,并开发了一个双分支自适应分布融合(Ada-DF)框架。一个辅助分支被构建来获得样本的标签分布。然后,通过每个情感的标签分布计算情感的类别分布。最后,根据注意权重动态地将这两个分布进行自适应融合,以训练目标分支。我们在三个真实世界数据集(RAF-DB,AffectNet和SFEW)上进行了广泛的实验,结果表明,与最先进的成果相比,我们的Ada-DF具有优势。
URL
https://arxiv.org/abs/2404.15714