However, unlike the existing public face datasets, in many real-world scenarios of face recognition, the depth of training dataset is shallow, which means only two face images are available for each ID.
This paper presents an effective solution to semi-supervised face recognition that is robust to the label noise aroused by the auto-labelling.
In this paper, we aim to address the challenge of NIR-VIS masked face recognition from the perspectives of training data and training method.
To start with, we present an overview of the end-to-end deep face recognition.
However, the correlation between hard positive and hard negative is overlooked, and so is the relation between the margins in positive and negative logits.
Extensive experiments on various benchmarks of face recognition show the proposed method significantly improves the training, not only in shallow face learning, but also for conventional deep face data.