Ada-DF: An Adaptive Label Distribution Fusion Network For Facial Expression Recognition
This work addresses annotation issues in facial expression recognition, which is important for applications in human-computer interaction, but it appears incremental as it builds on existing label distribution learning methods.
The paper tackles annotation ambiguity in facial expression recognition by proposing an adaptive label distribution fusion network, achieving state-of-the-art performance on datasets like RAF-DB, AffectNet, and SFEW.
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.