ProS: Facial Omni-Representation Learning via Prototype-based Self-Distillation
It addresses data collection and privacy challenges in facial analysis by enabling effective learning without annotated data, though it is incremental as it builds on self-distillation and prototype techniques.
This paper tackles the problem of unsupervised face representation learning by proposing ProS, a prototype-based self-distillation method that leverages unlabeled face images, achieving state-of-the-art performance on tasks like attribute estimation and expression recognition in both full and few-shot settings.
This paper presents a novel approach, called Prototype-based Self-Distillation (ProS), for unsupervised face representation learning. The existing supervised methods heavily rely on a large amount of annotated training facial data, which poses challenges in terms of data collection and privacy concerns. To address these issues, we propose ProS, which leverages a vast collection of unlabeled face images to learn a comprehensive facial omni-representation. In particular, ProS consists of two vision-transformers (teacher and student models) that are trained with different augmented images (cropping, blurring, coloring, etc.). Besides, we build a face-aware retrieval system along with augmentations to obtain the curated images comprising predominantly facial areas. To enhance the discrimination of learned features, we introduce a prototype-based matching loss that aligns the similarity distributions between features (teacher or student) and a set of learnable prototypes. After pre-training, the teacher vision transformer serves as a backbone for downstream tasks, including attribute estimation, expression recognition, and landmark alignment, achieved through simple fine-tuning with additional layers. Extensive experiments demonstrate that our method achieves state-of-the-art performance on various tasks, both in full and few-shot settings. Furthermore, we investigate pre-training with synthetic face images, and ProS exhibits promising performance in this scenario as well.