Back to articles
ACDM 2024 Digital Media Special Issue
Volume: 69 | Article ID: 010410
Image
Efficient Facial Expression Recognition Transformer with Additively Comprised Class Attention Encoder
  DOI :  10.2352/J.ImagingSci.Technol.2025.69.1.010410  Published OnlineJanuary 2025
Abstract
Abstract

Facial Expression Recognition (FER) models based on the Vision Transformer (ViT) have demonstrated promising performance on diverse datasets. However, the computational cost of the transformer encoder poses challenges in scenarios where strong computational resources are required. The utilization of large feature maps enhances expression information, but leads to a significant increase in token length. Consequently, the computational complexity grows quadratically with the length of the tokens as O(N2). Tasks involving large feature maps, such as high-resolution FER, encounter computational bottlenecks. To alleviate these challenges, we propose the Additively Comprised Class Attention Encoder as a substitute for the original ViT encoder, which reduces the complexity of the attention computation from O(N2) to O(N). Additionally, we introduce a novel token-level Squeeze-and-Excitation method to facilitate the model’s learning of more efficient representations. Experimental evaluations on the RAF-DB and FERplus datasets show that our approach can improve running speed by at least 27% (for 7 × 7 feature maps) while maintaining comparable accuracy, and it performs more efficiently on larger feature maps (about 49% speedup for 14 × 14 feature maps, and triple the speed for 28 × 28 feature maps).

Subject Areas :
Views 31
Downloads 17
 articleview.views 31
 articleview.downloads 17
  Cite this article 

Jiasen Wang, Yuanjing Hu, Aibin Huang, "Efficient Facial Expression Recognition Transformer with Additively Comprised Class Attention Encoderin Journal of Imaging Science and Technology,  2025,  pp 1 - 7,  https://doi.org/10.2352/J.ImagingSci.Technol.2025.69.1.010410

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2025
  Article timeline 
  • received May 2024
  • accepted October 2024
  • PublishedJanuary 2025

Preprint submitted to:
  Login or subscribe to view the content