Bayesian Convolutional Neural Networks for Seven Basic Facial Expression Classifications
This work addresses facial expression recognition for AI applications, but it is incremental as it builds on existing Bayesian neural network frameworks.
The paper tackles facial expression classification by proposing a Bayesian convolutional neural network (ResNet18_BNN) with improvements in objective function, training scheme, and parameter modeling, achieving 71.5% and 73.1% accuracy on FER2013 test sets.
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.