IEEE Trans Image Process. 2023;32:5231-5244. doi: 10.1109/TIP.2023.3309110. Epub 2023 Sep 20.
Near-infrared and visible face recognition (NIR-VIS) is attracting increasing attention because of the need to achieve face recognition in low-light conditions to enable 24-hour secure retrieval. However, annotating identity labels for a large number of heterogeneous face images is time-consuming and expensive, which limits the application of the NIR-VIS face recognition system to larger scale real-world scenarios. In this paper, we attempt to achieve NIR-VIS face recognition in an unsupervised domain adaptation manner. To get rid of the reliance on manual annotations, we propose a novel Robust cross-domain Pseudo-labeling and Contrastive learning (RPC) network which consists of three key components, i.e., NIR cluster-based Pseudo labels Sharing (NPS), Domain-specific cluster Contrastive Learning (DCL) and Inter-domain cluster Contrastive Learning (ICL). Firstly, NPS is presented to generate pseudo labels by exploring robust NIR clusters and sharing reliable label knowledge with VIS domain. Secondly, DCL is designed to learn intra-domain compact yet discriminative representations. Finally, ICL dynamically combines and refines intrinsic identity relationships to guide the instance-level features to learn robust and domain-independent representations. Extensive experiments are conducted to verify an accuracy of over 99% in pseudo label assignment and the advanced performance of RPC network on four mainstream NIR-VIS datasets.
近红外与可见光人脸识别（NIR-VIS）因其需要在低光照条件下实现人脸识别以实现 24 小时安全检索而受到越来越多的关注。然而，为大量异构人脸图像标注身份标签既耗时又昂贵，这限制了 NIR-VIS 人脸识别系统在更大规模真实场景中的应用。在本文中，我们尝试以无监督域自适应的方式实现 NIR-VIS 人脸识别。为了摆脱对人工标注的依赖，我们提出了一种新颖的鲁棒跨域伪标签共享和对比学习（RPC）网络，该网络由三个关键组件组成，即基于近红外聚类的伪标签共享（NPS）、特定于域的聚类对比学习（DCL）和域间聚类对比学习（ICL）。首先，通过探索稳健的近红外聚类并与可见光域共享可靠的标签知识，提出 NPS 来生成伪标签。其次，设计 DCL 来学习域内紧凑且有区分力的表示。最后，ICL 动态地组合和细化内在的身份关系，引导实例级特征学习稳健且与域无关的表示。在四个主流的 NIR-VIS 数据集上进行了广泛的实验，验证了伪标签分配的准确率超过 99%，以及 RPC 网络在先进性能方面的表现。
