Skip to content

A modified mobilenetV2 using selective kernels and coordinate attention for facial expression recognition

TL;DR

A modified MobileNetV2-based lightweight network that integrates Selective Kernel (SK) and Coordinate Attention (CA) modules to enhance feature extraction and spatial awareness while maintaining a low parameter count is proposed.

Abstract

Facial Expression Recognition (FER) plays an important role in human-computer interaction (HCI). However, most highly accurate FER models rely on complex and computationally heavy architectures that makes them unsuitable for low resource devices. This study proposes a modified MobileNetV2-based lightweight network that integrates Selective Kernel (SK) and Coordinate Attention (CA) modules to enhance feature extraction and spatial awareness while maintaining a low parameter count. The SK layer dynamically adapts receptive field sizes to capture both narrow and broad facial details. The CA module encodes both spatial and channel dependencies to help the network focus on emotion-specific regions such as the eyes, mouth, and eyebrows. The proposed model was trained and evaluated on two benchmark datasets, RAF-DB and FER-2013. Experimental results demonstrate that the model achieved 87.38% accuracy on RAF-DB and 70.39% accuracy on FER-2013 with only 1.07 million parameters and 0.687 GFLOPs. A Unity WebGL implementation also demonstrate real-time validation of the model’s ability.

View source

Similar papers

Open access Sep 2026

Facial expression recognition using CNNs and attention mechanisms on modified FER2013 dataset

Facial Expression Recognition (FER) is an important component of affective computing and human-computer interaction, yet it is difficult to apply in practice because of the variations in illumination, pose variation, occlusions, low-resolution images, and skew in the classes. To overcome these issues, this paper introd...

Aqeel Majeed Breesam, Roaa Safi Abed Alah, Mina Faris Ali Alnaimy · 0 citations
Sep 2026

Hybrid convolutional neural network with attention mechanism to provide robust face expression recognition

A hybrid model which uses several ResNet50 mixed with VGG16 backbones to improve the local facial features with the global context for a robust FER solu-tion, and shows superior robustness to occlusions and pose, even under cross-dataset testing.

Abderrahim Ouza, Mohamed El Ghmary, A. Choukri · 0 citations
Conference Open access Sep 2026

CNN Based Unimodal for Facial Emotion Recognition

ER plays an important role in improving HCI systems by enabling computer systems to detect and understand human emotions. In this study, a deep learning-based FER system is proposed which uses a pre-trained ResNet-50 Convolutional Neural Network model. The model is fine-tuned on CK+48 facial expression dataset to ident...

Rohan Gupta, Animesh Singh Visen, Adwey Anand · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.