Mitigating Label-Noise for Facial Expression Recognition in the Wild
Lists
Only you see this
Abstract
Label-noise constitutes a major challenge for facial expression recognition in the wild due to the ambiguity of facial expressions worsened by low-quality images. To deal with this problem, we propose a simple but effective Label-noise Robust Network (LRN) which explores the inter-class correlations for mitigating ambiguity that usually happens between morphologically similar classes. Specifically, LRN leverages a multivariate normal distribution to model such correlations at the final hidden layer of the neural network to suppress the heteroscedastic uncertainty caused by inter-class label noise. Furthermore, LRN utilizes a confidence-based label-free loss to extract compact intra-class feature representations under label noise while preserving the intrinsic inter-class relationships. Experiments on three in-the-wild facial expression datasets demonstrates the superiority of our method.
BibTeX
@inproceedings{yan2022mitigating,
author = {Huan Yan and Yu Gu and Xiang Zhang and Yantong Wang and Yusheng Ji and Fuji Ren},
title = {{Mitigating Label-Noise for Facial Expression Recognition in the Wild}},
booktitle = {ICME},
year = {2022},
doi = {10.1109/icme52920.2022.9859818},
}Loading related content...