LAFS: Landmark-based Facial Self-supervised Learning for Face Recognition
This work addresses the challenge of training effective face recognition models in the absence of labeled data, which is incremental as it builds on existing self-supervised and landmark-based approaches.
The paper tackled the problem of learning facial representations for face recognition without labels by using self-supervised pretraining with landmark-based patches and augmentations, achieving significant improvements over state-of-the-art methods on multiple benchmarks, particularly in few-shot scenarios.
In this work we focus on learning facial representations that can be adapted to train effective face recognition models, particularly in the absence of labels. Firstly, compared with existing labelled face datasets, a vastly larger magnitude of unlabeled faces exists in the real world. We explore the learning strategy of these unlabeled facial images through self-supervised pretraining to transfer generalized face recognition performance. Moreover, motivated by one recent finding, that is, the face saliency area is critical for face recognition, in contrast to utilizing random cropped blocks of images for constructing augmentations in pretraining, we utilize patches localized by extracted facial landmarks. This enables our method - namely LAndmark-based Facial Self-supervised learning LAFS), to learn key representation that is more critical for face recognition. We also incorporate two landmark-specific augmentations which introduce more diversity of landmark information to further regularize the learning. With learned landmark-based facial representations, we further adapt the representation for face recognition with regularization mitigating variations in landmark positions. Our method achieves significant improvement over the state-of-the-art on multiple face recognition benchmarks, especially on more challenging few-shot scenarios.