ResEmoteNet: Bridging Accuracy and Loss Reduction in Facial Emotion Recognition

TL;DR

ResEmoteNet is a new deep learning architecture combining convolutional, squeeze-excitation, and residual blocks, significantly improving facial emotion recognition accuracy across multiple datasets by focusing on important facial features.

Contribution

Introduces ResEmoteNet, a novel architecture that integrates SE and residual blocks to enhance feature representation and reduce loss in facial emotion recognition.

Findings

Achieved state-of-the-art accuracy on four datasets

Outperformed existing models in facial emotion recognition

Demonstrated effective feature focus with SE blocks

Abstract

The human face is a silent communicator, expressing emotions and thoughts through its facial expressions. With the advancements in computer vision in recent years, facial emotion recognition technology has made significant strides, enabling machines to decode the intricacies of facial cues. In this work, we propose ResEmoteNet, a novel deep learning architecture for facial emotion recognition designed with the combination of Convolutional, Squeeze-Excitation (SE) and Residual Networks. The inclusion of SE block selectively focuses on the important features of the human face, enhances the feature representation and suppresses the less relevant ones. This helps in reducing the loss and enhancing the overall model performance. We also integrate the SE block with three residual blocks that help in learning more complex representation of the data through deeper layers. We evaluated ResEmoteNet on four open-source databases: FER2013, RAF-DB, AffectNet-7 and ExpW, achieving accuracies of 79.79%, 94.76%, 72.39% and 75.67% respectively. The proposed network outperforms state-of-the-art models across all four databases. The source code for ResEmoteNet is available at https://github.com/ArnabKumarRoy02/ResEmoteNet.