Bayesian Convolutional Neural Networks for Seven Basic Facial Expression Classifications

2021/07/10 by Yuan Tai, Tai, Yuan, Yihua Tan +5 · 1 citation
Computer Science · Psychology · #Activation function #Artificial intelligence #Artificial neural network #Bayesian network #Bayesian probability #Blind Source Separation Techniques #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Convolution (computer science) #Convolutional neural network #Cross entropy #Emotion and Mood Recognition #Entropy (arrow of time) #Expression (computer science) #FOS: Computer and information sciences #Face and Expression Recognition #Facial expression #Function (biology) #Machine learning #Pattern recognition (psychology) #Set (abstract data type) #Test set #cs.CV

paper · pdf · doi:10.48550/arxiv.2107.04834

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2021/07/10 · arxiv created 2021/07/13 · arxiv updated 2021/07/14 · openalex created_date 2021/07/19 · openalex updated_date 2026/08/08

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.

Citations

• Facial Expression Recognition using Convolutional Neural Networks: State of the Art
• Weight Uncertainty in Neural Networks
• Face Behavior a la carte: Expressions, Affect and Action Units in a Single Network
• Affect Analysis in-the-wild: Valence-Arousal, Expressions, Action Units and a Unified Framework
• Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Study

Related

• Facial Emotion Recognition using Convolutional Neural Networks
• Hey Human, If your Facial Emotions are Uncertain, You Should Use Bayesian Neural Networks!
• Convolutional Neural Networks for Facial Expression Recognition
• Facial Emotions Recognition using Convolutional Neural Net
• DeXpression: Deep Convolutional Neural Network for Expression Recognition