arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2107.04834cs.CV
收藏

基于贝叶斯卷积神经网络的七种基本表情分类

Bayesian Convolutional Neural Networks for Seven Basic Facial Expression Classifications

Yuan Tai, Yihua Tan, Wei Gong, Hailan Huang

摘要:

7种基本的面部表情分类是表达人类复杂情感的一种基本方式,是人工智能研究的重要组成部分。本文在传统贝叶斯神经网络框架的基础上,对所构建的ResNet18_BNN网络进行了以下三个方面的改进:(1)提出了一种新的目标函数,该目标函数由不确定参数的KL损失和特定参数的交集组成。熵损失合成。(2)针对一种特殊的目标函数,提出了交替更新这两个参数的训练方案。(3)仅对最后一个卷积组的参数建模。通过在FER2013测试集上的测试,我们在PublicTestSet和PrivateTestSet上分别获得了71.5%和73.1%的准确率。与传统的贝叶斯神经网络相比,该方法带来了最高的分类精度增益。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑