Purposeful Regularization with Reinforcement Learning for Facial Expression Recognition In-the-Wild

Sanghwa Hong; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024, pp. 4615-4624

Facial Expression Recognition (FER) an essential aspect of emotion analysis through artificial intelligence is a crucial research area for applications across healthcare and entertainment. Although traditional approaches utilizing Convolutional Neural Networks (CNNs) for analyzing human emotions from facial expressions achieve superior accuracy over conventional machine learning methods overfitting --especially arising severely from data collected in uncontrolled In-the-wild settings --significantly impede CNNs performance. This is due to the data scarcity and inherent noise inside In-the-wild data. To address this challenge this paper introduces a novel regularization method that employs Reinforcement Learning (RL) to adaptively apply regularization hyperparameters appropriate for the evolving state of trained CNNs. Through experiments on various dataset such as CIFAR100 FER2013 and AffectNet datasets including diverse perspective analysis such as graphical Grad-CAM and numerical analysis it is demonstrated that the suggested method can alleviate memorization of noise in training data and promote learning of essential features. The significance of the suggested method lies in its demonstrated remarkable effectiveness in enhancing CNNs' generalization and reducing overfitting.