论文标题
视觉变压器的零件面部识别
Part-based Face Recognition with Vision Transformers
论文作者
论文摘要
使用CNN和基于保证金的损失的整体方法占据了面部识别的研究。在这项工作中，我们以两种方式偏离了这种环境：（a）我们采用视觉变压器作为培训面部识别非常强大的基线的建筑，简单地称为FVIT，它已经超过了大多数最先进的面部识别方法。 （b）其次，我们利用了从不规则网格中提取的处理信息（视觉令牌）的变压器的固有属性，以设计面部识别管道，以使人联想到基于部分的面部识别方法。我们的管道称为零件FVIT，仅包括一个轻巧的网络，以预测面部地标的坐标，然后是视觉变压器在从预测地标提取的贴片上运行的视觉变压器，并且在没有地标监督的情况下，它是经过训练的端到端训练的。通过学习提取歧视性斑块，我们的部分变压器进一步提高了视觉变压器基线的准确性，从而在几个面部识别基准上实现了最新的准确性。
Holistic methods using CNNs and margin-based losses have dominated research on face recognition. In this work, we depart from this setting in two ways: (a) we employ the Vision Transformer as an architecture for training a very strong baseline for face recognition, simply called fViT, which already surpasses most state-of-the-art face recognition methods. (b) Secondly, we capitalize on the Transformer's inherent property to process information (visual tokens) extracted from irregular grids to devise a pipeline for face recognition which is reminiscent of part-based face recognition methods. Our pipeline, called part fViT, simply comprises a lightweight network to predict the coordinates of facial landmarks followed by the Vision Transformer operating on patches extracted from the predicted landmarks, and it is trained end-to-end with no landmark supervision. By learning to extract discriminative patches, our part-based Transformer further boosts the accuracy of our Vision Transformer baseline achieving state-of-the-art accuracy on several face recognition benchmarks.
