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.

翻译：本文提出了一种名为原型自蒸馏（ProS）的新方法，用于无监督人脸表示学习。现有监督方法严重依赖大量标注的人脸训练数据，这带来了数据收集和隐私方面的挑战。为应对这些问题，我们提出ProS，利用大规模未标注人脸图像学习全面的人脸全表示。具体而言，ProS包含两个视觉变换器（教师和学生模型），它们通过不同的增强图像（裁剪、模糊、着色等）进行训练。此外，我们构建了一个人脸感知检索系统，结合数据增强获取主要包含人脸区域的精选图像。为增强学习特征的判别能力，我们引入了一种基于原型的匹配损失，该损失对齐特征（教师或学生）与一组可学习原型之间的相似性分布。预训练后，教师视觉变换器作为主干网络，通过附加层的简单微调即可完成下游任务，包括属性估计、表情识别和关键点对齐。大量实验表明，我们的方法在完整和少样本设置下的多种任务中均达到了最先进性能。此外，我们还研究了使用合成人脸图像进行预训练，ProS在此场景下也表现出色。