.png){kind=icon}
返回
Uncertain Facial Expression Recognition via Multi-Task Assisted Correction
.png){kind=icon}
OA
AI
DOI：10.1109/TMM.2023.3301209.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep models for facial expression recognition achieve high performance by training on large-scale labeled data. However, publicly available datasets contain uncertain facial expressions caused by ambiguous annotations or confusing emotions, which could severely decline the robustness. Previous studies usually follow the bias elimination method in general tasks without considering the uncertainty problem from the perspective of different corresponding sources. This article proposes a novel method of multi-task assisted correction in addressing uncertain facial expression recognition called MTAC. Specifically, a confidence estimation block and a weighted regularization module are applied to highlight solid samples and suppress uncertain samples in every batch. In addition, two auxiliary tasks, i.e., action unit detection and valence-arousal measurement, are introduced to learn semantic distributions from a data-driven AU graph and mitigate category imbalance based on latent dependencies between discrete and continuous emotions, respectively. Moreover, a re-labeling strategy guided by feature-level similarity constraint further generates new labels for identified uncertain samples to promote model learning. The proposed method can flexibly combine with existing frameworks in a fully-supervised or weakly-supervised manner. Experiments on five popular benchmarks demonstrate that the MTAC substantially improves over baselines when facing synthetic and real uncertainties and outperforms the state-of-the-art methods.
Keyword:
Facial expression recognition
uncertainty
action unit
valence
arousal
multi-task learning
期刊
IF:
9.7
论文数:
4.5K
被引数:
2.4W
机构
引用论文
分享收藏Inflexibility of mental planning: A characteristic disorder with prefrontal lobe lesions?心理计划的僵化: 前额叶病变的特征性障碍？
PREAI
分享收藏Random vibration and reliability analysis of fluid-conveying pipe under white noise excitations
PREAI
分享收藏Activation of the TLR/MyD88/NF-κB Signal Pathway Contributes to Changes in IL-4 and IL-12 Production in Piglet Lymphocytes Infected with Porcine Circovirus Type 2 In Vitro.png)
PLoS ONEOAAI
PLoS ONEIF0
OAAI分享收藏分享收藏
查看更多内容