We propose a novel Dynamic Restrained Uncertainty Weighting Loss to experimentally handle the problem of balancing the contributions of multiple tasks on the ICML ExVo 2022 Challenge. The multitask aims to recognize expressed emotions and demographic traits from vocal bursts jointly. Our strategy combines the advantages of Uncertainty Weight and Dynamic Weight Average, by extending weights with a restraint term to make the learning process more explainable. We use a lightweight multi-exit CNN architecture to implement our proposed loss approach. The experimental H-Mean score (0.394) shows a substantial improvement over the baseline H-Mean score (0.335).
@article{arxiv.2206.11049,
title = {Dynamic Restrained Uncertainty Weighting Loss for Multitask Learning of Vocal Expression},
author = {Meishu Song and Zijiang Yang and Andreas Triantafyllopoulos and Xin Jing and Vincent Karas and Xie Jiangjian and Zixing Zhang and Yamamoto Yoshiharu and Bjoern W. Schuller},
journal= {arXiv preprint arXiv:2206.11049},
year = {2022}
}