LAFS：基于 landmarks 的人脸自监督学习用于人脸识别
LAFS: Landmark-based Facial Self-supervised Learning for Face Recognition
AI总结：
针对无标签人脸识别，提出基于 landmarks 的自监督方法 LAFS，利用人脸关键点补丁和特定增强学习关键表示，在多个基准上显著提升性能，尤其在少样本场景。
摘要：
在这项工作中，我们专注于学习可适应训练有效人脸识别模型的人脸表示，特别是在缺乏标签的情况下。首先，与现有的带标签人脸数据集相比，现实世界中存在数量大得多的未标记人脸。我们通过自监督预训练探索这些未标记人脸图像的学习策略，以迁移泛化的人脸识别性能。此外，受最近一项发现的启发，即人脸显著区域对人脸识别至关重要，与在预训练中利用随机裁剪的图像块构建增强不同，我们利用由提取的人脸 landmarks 定位的补丁。这使得我们的方法——即基于 landmarks 的人脸自监督学习（LAFS）——能够学习对人脸识别更关键的关键表示。我们还整合了两种 landmark 特定的增强，引入更多 landmark 信息的多样性，以进一步正则化学习。利用学习到的基于 landmarks 的人脸表示，我们进一步调整表示用于人脸识别，并通过正则化减轻 landmark 位置的变化。我们的方法在多个面部识别基准上显著优于现有最先进方法，尤其是在更具挑战性的少样本场景中。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
