论文标题
在看不见的域中学习元面部识别
Learning Meta Face Recognition in Unseen Domains
论文作者
论文摘要
面部识别系统通常在现实世界中面临着看不见的领域,并且由于其概括不佳而表现出不令人满意的性能。例如,WebFace数据上的训练有素的模型无法处理监视方案中的ID与点任务。在本文中,我们旨在学习一个通用模型,该模型可以直接处理新的看不见的域而无需任何模型更新。为此,我们通过元学习的元识别(MFR)提出了一种新颖的面部识别方法。 MFR通过元优化目标综合源/目标域移动,该目标要求模型不仅要了解合成源域的有效表示,而且还要在合成目标域上学习有效表示。具体而言,我们通过域级采样策略构建域转移批次,并通过优化多域分布来在合成的源/目标域上获得后传达的梯度/元梯度。进一步合并了梯度和元梯度以更新模型以改善概括。此外,我们提出了两个用于广义面部识别评估的基准。与几个基线和其他最先进的基准相比,基准上的实验验证了我们方法的概括。拟议的基准将在https://github.com/cleardusk/mfr上找到。
Face recognition systems are usually faced with unseen domains in real-world applications and show unsatisfactory performance due to their poor generalization. For example, a well-trained model on webface data cannot deal with the ID vs. Spot task in surveillance scenario. In this paper, we aim to learn a generalized model that can directly handle new unseen domains without any model updating. To this end, we propose a novel face recognition method via meta-learning named Meta Face Recognition (MFR). MFR synthesizes the source/target domain shift with a meta-optimization objective, which requires the model to learn effective representations not only on synthesized source domains but also on synthesized target domains. Specifically, we build domain-shift batches through a domain-level sampling strategy and get back-propagated gradients/meta-gradients on synthesized source/target domains by optimizing multi-domain distributions. The gradients and meta-gradients are further combined to update the model to improve generalization. Besides, we propose two benchmarks for generalized face recognition evaluation. Experiments on our benchmarks validate the generalization of our method compared to several baselines and other state-of-the-arts. The proposed benchmarks will be available at https://github.com/cleardusk/MFR.