General Facial Representation Learning in a Visual-Linguistic Manner

TL;DR

This paper introduces FaRL, a visual-linguistic framework for learning universal facial representations that improve performance across various face analysis tasks by combining contrastive learning and masked image modeling.

Contribution

The paper proposes a novel framework, FaRL, that leverages both high-level semantic and low-level information for facial representation learning, outperforming existing models.

Findings

FaRL achieves superior transfer performance on multiple face analysis tasks.

It outperforms previous models especially in low-data regimes.

Surpasses state-of-the-art methods on face parsing and face alignment.

Abstract

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.