Recent state-of-the-art face recognition (FR) approaches have achieved impressive performance, yet unconstrained face recognition still represents an open problem. Face image quality assessment (FIQA) approaches aim to estimate the quality of the input samples that can help provide information on the confidence of the recognition decision and eventually lead to improved results in challenging scenarios. While much progress has been made in face image quality assessment in recent years, computing reliable quality scores for diverse facial images and FR models remains challenging. In this paper, we propose a novel approach to face image quality assessment, called FaceQAN, that is based on adversarial examples and relies on the analysis of adversarial noise which can be calculated with any FR model learned by using some form of gradient descent. As such, the proposed approach is the first to link image quality to adversarial attacks. Comprehensive (cross-model as well as model-specific) experiments are conducted with four benchmark datasets, i.e., LFW, CFP-FP, XQLFW and IJB-C, four FR models, i.e., CosFace, ArcFace, CurricularFace and ElasticFace, and in comparison to seven state-of-the-art FIQA methods to demonstrate the performance of FaceQAN. Experimental results show that FaceQAN achieves competitive results, while exhibiting several desirable characteristics.
翻译:最近最先进的面部识别(FR)方法取得了令人印象深刻的成绩,但不受约束的面部识别(FIQA)方法仍是一个尚未解决的问题。面部图像质量评估(FIQA)方法旨在估计投入样本的质量,以便帮助提供信息,说明对承认决定的信心,并最终在具有挑战性的情景中取得更好的结果。虽然近年来在面部质量评估方面取得了很大进展,但为不同面部图像和FR模型计算可靠的质量分数仍然具有挑战性。在本文中,我们提议采用新的方法,即所谓的FaceQAN(FaceQAN)来进行图像质量评估。FaceQAN(Face ),该方法以对抗性实例为基础,并依赖对通过使用某种梯度下降形式学习的任何FR模型所得出的对抗性噪音的分析。因此,拟议方法首先将图像质量与对抗性攻击联系起来。全面(跨模型和特定模型)实验有四个基准数据集,即:LFW、CFFP-FP、XQLFW和IJB-C、FR 4模型,即C-CFIS FOS、Arceface-FAS-A和E-A-AFI-S-S-S-S-S-FIFIFAx-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-FAx-FAx-S-S-S-S-FI 和FIFIFAFAx-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-FA-FA-FAFAFA-FA-FA-FA-FA-FA-FA-FA-S-S-S-S-S-S-S-S-S-S-S-S-S-FA-FA-S-FA-FA-S-S-FA-