SwinFace: A Multi-task Transformer for Face Recognition, Expression Recognition, Age Estimation and Attribute Estimation

TL;DR

SwinFace is a multi-task transformer model that simultaneously performs face recognition, expression recognition, age estimation, and attribute prediction, improving accuracy and efficiency through shared features and task-specific modules.

Contribution

The paper introduces SwinFace, a unified multi-task transformer architecture with a novel Multi-Level Channel Attention module for improved face analysis performance.

Findings

Achieves state-of-the-art accuracy on facial expression recognition.

Attains 0.22 ε-error on age estimation benchmark.

Demonstrates superior multi-task learning capabilities.

Abstract

In recent years, vision transformers have been introduced into face recognition and analysis and have achieved performance breakthroughs. However, most previous methods generally train a single model or an ensemble of models to perform the desired task, which ignores the synergy among different tasks and fails to achieve improved prediction accuracy, increased data efficiency, and reduced training time. This paper presents a multi-purpose algorithm for simultaneous face recognition, facial expression recognition, age estimation, and face attribute estimation (40 attributes including gender) based on a single Swin Transformer. Our design, the SwinFace, consists of a single shared backbone together with a subnet for each set of related tasks. To address the conflicts among multiple tasks and meet the different demands of tasks, a Multi-Level Channel Attention (MLCA) module is integrated into each task-specific analysis subnet, which can adaptively select the features from optimal levels and channels to perform the desired tasks. Extensive experiments show that the proposed model has a better understanding of the face and achieves excellent performance for all tasks. Especially, it achieves 90.97% accuracy on RAF-DB and 0.22 $\epsilon$-error on CLAP2015, which are state-of-the-art results on facial expression recognition and age estimation respectively. The code and models will be made publicly available at https://github.com/lxq1000/SwinFace.