arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2208.02417cs.CV
收藏

基于两特征间嵌入关系和坐标的NIR-VIS人脸识别

NIR-to-VIS Face Recognition via Embedding Relations and Coordinates of the Pairwise Features

Yonsei University(延世大学)

MyeongAh Cho, Tae-young Chun, g Taeoh Kim, Sangyoun Lee

摘要:

近红外到可见光人脸识别是通过提取领域不变的特征来识别两个不同领域的人脸。然而,这是一个具有挑战性的问题,由于这两个不同的领域的特点,并缺乏近红外人脸数据集。为了减少域差异,同时使用现有的人脸识别模型,我们提出了一个“关系模块”,它可以简单地添加到任何人脸识别模型。从人脸图像中提取的局部特征包含了人脸各个部分的信息。基于两种不同的领域特征,使用局部特征之间的关系比直接使用它更具领域不变性。除了这些关系之外,诸如从嘴唇到下巴或眼睛到眼睛的距离的位置信息也提供域不变信息。在我们的关系模块中,关系层隐式地捕获关系,坐标层对位置信息进行建模。此外,我们提出的具有条件保证金的三重损失减少了训练中的类内变化,并导致额外的性能改进。与一般的人脸识别模型不同,我们的附加模块不需要使用大规模数据集进行预训练。建议的模块微调仅与CASIA NIR-VIS 2.0数据库。与两个基线模型相比,我们实现了14.81%的rank-1准确率和15.47%的验证率,FAR提高了0.1%。

英文摘要:

NIR-to-VIS face recognition is identifying faces of two different domains by extracting domain-invariant features. However, this is a challenging problem due to the two different domain characteristics, and the lack of NIR face dataset. In order to reduce domain discrepancy while using the existing face recognition models, we propose a 'Relation Module' which can simply add-on to any face recognition models. The local features extracted from face image contain information of each component of the face. Based on two different domain characteristics, to use the relationships between local features is more domain-invariant than to use it as it is. In addition to these relationships, positional information such as distance from lips to chin or eye to eye, also provides domain-invariant information. In our Relation Module, Relation Layer implicitly captures relationships, and Coordinates Layer models the positional information. Also, our proposed Triplet loss with conditional margin reduces intra-class variation in training, and resulting in additional performance improvements. Different from the general face recognition models, our add-on module does not need to pre-train with the large scale dataset. The proposed module fine-tuned only with CASIA NIR-VIS 2.0 database. With the proposed module, we achieve 14.81% rank-1 accuracy and 15.47% verification rate of 0.1% FAR improvements compare to two baseline models.

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。

↑