Face Expression Recognition via transformer-based classification models

Authors : Muhammed Cihad Arslanoğlu, Hüseyin Acar, Abdülkadir Albayrak

Pages : 214-223

Doi:10.17694/bajece.1486140

View : 157 | Download : 200

Publication Date : 2024-09-30

Article Type : Research Paper

Abstract :Facial Expression Recognition (FER) tasks have widely studied in the literature since it has many applications. Fast development of technology in deep learning computer vision algorithms, especially, transformer-based classification models, makes it hard to select most appropriate models. Using complex model may increase accuracy performance but decreasing inference time which is a crucial in near real-time applications. On the other hand, small models may not give desired results. In this study, we aimed to examine performance of 5 different relatively small transformer-based image classification algorithms for FER tasks. We used vanilla ViT, PiT, Swin, DeiT, and CrossViT with considering their trainable parameter size and architectures. Each model has 20-30M trainable parameters which means relatively small. Moreover, each model has different architectures. As an illustration, CrossViT focuses on image using multi-scale patches and PiT model introduces convolution layers and pooling techniques to vanilla ViT model. We obtained all results for widely used FER datasets: CK+ and KDEF. We observed that, PiT model achieves the best accuracy scores 0.9513 and 0.9090 for CK+ and KDEF datasets, respectively
Keywords : FER, Transformers, ViT, Classification