How to learn a universal facial representation that boosts all face analysis tasks? This paper takes one step toward this goal. In this paper, we study the transfer performance of pre-trained models on face analysis tasks and introduce a framework, called FaRL, for general Facial Representation Learning in a visual-linguistic manner. On one hand, the framework involves a contrastive loss to learn high-level semantic meaning from image-text pairs. On the other hand, we propose exploring low-level information simultaneously to further enhance the face representation, by adding a masked image modeling. We perform pre-training on LAION-FACE, a dataset containing large amount of face image-text pairs, and evaluate the representation capability on multiple downstream tasks. We show that FaRL achieves better transfer performance compared with previous pre-trained models. We also verify its superiority in the low-data regime. More importantly, our model surpasses the state-of-the-art methods on face analysis tasks including face parsing and face alignment.
@article{arxiv.2112.03109,
title = {General Facial Representation Learning in a Visual-Linguistic Manner},
author = {Yinglin Zheng and Hao Yang and Ting Zhang and Jianmin Bao and Dongdong Chen and Yangyu Huang and Lu Yuan and Dong Chen and Ming Zeng and Fang Wen},
journal= {arXiv preprint arXiv:2112.03109},
year = {2022}
}