Dynamic Noise Injection for Facial Expression Recognition In-the-Wild

SangHwa Hong, Jin-Woo Jeong; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2023, pp. 5709-5715

Abstract

Facial expression-based emotion analysis is one of the most important artificial intelligence research fields. However, a lot of works still suffer from the low classification/regression performance caused by overfitting. Therefore, this paper proposes a new noise injection technique to alleviate this problem. Specifically, based on the ResNet-18 architecture, we dynamically add feature-level noise into the BN+ReLU unit to learn more robust features. Experiments on facial expression classification with the AffectNet dataset demonstrated the usefulness of the proposed approach.

Related Material

[pdf]
[bibtex]
@InProceedings{Hong_2023_CVPR, author = {Hong, SangHwa and Jeong, Jin-Woo}, title = {Dynamic Noise Injection for Facial Expression Recognition In-the-Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {5709-5715} }