Bayesian Convolutional Neural Networks for Seven Basic Facial Expression Classifications
arXiv:2107.04834
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.
References in corpus (4)
- Weight Uncertainty in Neural Networks
- Facial Expression Recognition using Convolutional Neural Networks: State of the Art
- Affect Analysis in-the-wild: Valence-Arousal, Expressions, Action Units and a Unified Framework
- Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFace