Abstract
An important aspect of deploying face recognition (FR) algorithms in real-world applications is their ability to learn new face identities from a continuous data stream. However, the online training of existing deep neural network-based FR algorithms, which are pre-trained offline on large-scale stationary datasets, encounter two major challenges: (I) catastrophic forgetting of previously learned identities, and (II) the need to store past data for complete retraining from scratch, leading to significant storage constraints and privacy concerns. In this paper, we introduce CLFace, a continual learning framework designed to preserve and incrementally extend the learned knowledge. CLFace eliminates the classification layer, resulting in a resource-efficient FR model that remains fixed throughout lifelong learning and provides label-free supervision to a student model, making it suitable for open-set face recognition during incremental steps. We introduce an objective function that employs feature-level distillation to reduce drift between feature maps of the student and teacher models across multiple stages. Additionally, it incorporates a geometry-preserving distillation scheme to maintain the orientation of the teacher model's feature embedding. Furthermore, a contrastive knowledge distillation is incorporated to continually enhance the discriminative power of the feature representation by matching similarities between new identities. Experiments on several benchmark FR datasets demonstrate that CLFace outperforms baseline approaches and state-of-the-art methods on unseen identities using both in-domain and out-of-domain datasets.
Abstract (translated)
将面部识别（FR）算法部署到实际应用中的一个重要方面是其从连续数据流中学习新面孔身份的能力。然而，现有的基于深度神经网络的FR算法已经离线在大规模静态数据集上预训练，在在线训练时会遇到两个主要挑战：(I) 忘记之前已学过的身份信息（灾难性遗忘），以及 (II) 需要存储过去的数据以从头开始进行完全重新训练，这导致了显著的存储限制和隐私问题。在本文中，我们介绍了CLFace，这是一个设计用于保存并逐渐扩展所学习知识的持续学习框架。CLFace消除了分类层，从而形成一个在整个终身学习过程中保持不变且资源高效的FR模型，并为学生模型提供无标签监督，使其适合于增量步骤中的开放集面部识别。我们引入了一个目标函数，该函数利用特征级蒸馏来减少学生和教师模型在多个阶段之间的特征图之间的漂移。此外，它还采用了一种保几何结构的蒸馏方案以保持教师模型特征嵌入的方向。另外，还结合了对比知识蒸馏，通过匹配新身份间的相似性，持续增强特征表示的判别能力。实验结果表明，在几个基准FR数据集上，CLFace在未见过的身份识别性能方面超过了基线方法和最先进的方法，并且这些结果是在使用域内和域外数据时都得到了证实。
URL
https://arxiv.org/abs/2411.13886
