Bayesian Convolutional Neural Networks for Seven Basic Facial Expression Classifications
Abstract
The seven basic facial expression classifications are a basic way to express complex human emotions and are an important part of artificial intelligence research. Based on the traditional Bayesian neural network framework, the ResNet18_BNN network constructed in this paper has been improved in the following three aspects: (1) A new objective function is proposed, which is composed of the KL loss of uncertain parameters and the intersection of specific parameters. Entropy loss composition. (2) Aiming at a special objective function, a training scheme for alternately updating these two parameters is proposed. (3) Only model the parameters of the last convolution group. Through testing on the FER2013 test set, we achieved 71.5% and 73.1% accuracy in PublicTestSet and PrivateTestSet, respectively. Compared with traditional Bayesian neural networks, our method brings the highest classification accuracy gain.
Cite
@article{arxiv.2107.04834,
title = {Bayesian Convolutional Neural Networks for Seven Basic Facial Expression Classifications},
author = {Yuan Tai and Yihua Tan and Wei Gong and Hailan Huang},
journal= {arXiv preprint arXiv:2107.04834},
year = {2021}
}