MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition

by   Licai Sun, et al.

Dynamic facial expression recognition (DFER) is essential to the development of intelligent and empathetic machines. Prior efforts in this field mainly fall into supervised learning paradigm, which is severely restricted by the limited labeled data in existing datasets. Inspired by recent unprecedented success of masked autoencoders (e.g., VideoMAE), this paper proposes MAE-DFER, a novel self-supervised method which leverages large-scale self-supervised pre-training on abundant unlabeled data to largely advance the development of DFER. Since the vanilla Vision Transformer (ViT) employed in VideoMAE requires substantial computation during fine-tuning, MAE-DFER develops an efficient local-global interaction Transformer (LGI-Former) as the encoder. Moreover, in addition to the standalone appearance content reconstruction in VideoMAE, MAE-DFER also introduces explicit temporal facial motion modeling to encourage LGI-Former to excavate both static appearance and dynamic motion information. Extensive experiments on six datasets show that MAE-DFER consistently outperforms state-of-the-art supervised methods by significant margins (e.g., +6.30% UAR on DFEW and +8.34% UAR on MAFW), verifying that it can learn powerful dynamic facial representations via large-scale self-supervised pre-training. Besides, it has comparable or even better performance than VideoMAE, while largely reducing the computational cost (about 38% FLOPs). We believe MAE-DFER has paved a new way for the advancement of DFER and can inspire more relevant research in this field and even other related tasks. Codes and models are publicly available at


page 1

page 4

page 8

page 9

page 15

page 16

page 17


Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training

Self-supervised learning of speech representations has been a very activ...

Exploring Expression-related Self-supervised Learning for Affective Behaviour Analysis

This paper explores an expression-related self-supervised learning (SSL)...

Using Self-Supervised Co-Training to Improve Facial Representation

In this paper, at first, the impact of ImageNet pre-training on Facial E...

Masked Motion Predictors are Strong 3D Action Representation Learners

In 3D human action recognition, limited supervised data makes it challen...

Prompting Visual-Language Models for Dynamic Facial Expression Recognition

This paper presents a novel visual-language model called DFER-CLIP, whic...

VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

Pre-training video transformers on extra large-scale datasets is general...

ViTASD: Robust Vision Transformer Baselines for Autism Spectrum Disorder Facial Diagnosis

Autism spectrum disorder (ASD) is a lifelong neurodevelopmental disorder...

Please sign up or login with your details

Forgot password? Click here to reset