Recognition in low quality face datasets is challenging because facial attributes are obscured and degraded. Advances in margin-based loss functions have resulted in enhanced discriminability of faces in the embedding space. Further, previous studies have studied the effect of adaptive losses to assign more importance to misclassified (hard) examples. In this work, we introduce another aspect of adaptiveness in the loss function, namely the image quality. We argue that the strategy to emphasize misclassified samples should be adjusted according to their image quality. Specifically, the relative importance of easy or hard samples should be based on the sample's image quality. We propose a new loss function that emphasizes samples of different difficulties based on their image quality. Our method achieves this in the form of an adaptive margin function by approximating the image quality with feature norms. Extensive experiments show that our method, AdaFace, improves the face recognition performance over the state-of-the-art (SoTA) on four datasets (IJB-B, IJB-C, IJB-S and TinyFace). Code and models are released in https://github.com/mk-minchul/AdaFace.
翻译:由于面部特征模糊和退化,对低质量脸部数据集的认知具有挑战性,因为面部特征模糊和退化。基于边际损失功能的进展导致嵌入空间面部的分布更加不均。此外,先前的研究还研究了适应性损失的影响,以更加重视错误分类(硬)实例。在这项工作中,我们引入了损失功能适应性的另一个方面,即图像质量。我们主张,应当根据图像质量调整强调错误分类样本的战略。具体地说,简单或硬样本的相对重要性应当基于样本的图像质量。我们提出了一个新的损失功能,根据图像质量强调不同困难样本的样本。我们的方法以适应性边际功能的形式实现了这一效果,即与特征规范相近。广泛的实验表明,我们的方法AdaFaface改进了四个数据集(IJB-B、IJB-C、IJB-S和TiniyFace)的面容识别性表现(IJB-C、IJB-S和TyFace Face)的面容和模型。在 https://githuls/Am-mk-sting/Fashin/Fase/Fase/Fasesting/Fase/Fase-sting/Fase/Fastech/Fac/Fac/Fac/Fard/Fax/Fax/Fax/Fac/FAS-S)中发布。代码和模型和模型和模型。