论文标题
FaceQan：通过对抗噪声探索的面部图像质量评估
FaceQAN: Face Image Quality Assessment Through Adversarial Noise Exploration
论文作者
论文摘要
最近的最新面部识别方法（FR）方法取得了令人印象深刻的表现，但不受约束的面部识别仍然代表了一个开放的问题。面部图像质量评估（FIQA）方法旨在估算输入样本的质量，以帮助提供有关识别决策信心的信息，并最终在具有挑战性的情况下提高结果。尽管近年来在面部图像质量评估中取得了很多进展，但计算出可靠的面部图像和FR模型的可靠质量得分仍然具有挑战性。在本文中，我们提出了一种新的方法来面对图像质量评估，称为faceqan，该方法基于对抗性示例，并依赖于对对抗噪声的分析，该分析可以通过使用某种形式的梯度下降来学习的任何FR模型来计算。因此，提出的方法是第一个将图像质量与对抗性攻击联系起来的方法。使用四个基准数据集（即LFW，CFP-FP，XQLFW和IJB-C，四个FR模型，即界面，弧形，课程，课程和弹性面，以及与七个尚未达到Teash-Art Fieqa的表面face face face face face face face s face qussive face face face quse face quse face quse face quse face q q q q q qute face q q q q q q qute cormession face q q q q q face q q q q face q q q q q face q q q q q face qus，实验结果表明，FaceQan在表现出几种理想特征的同时取得了竞争成果。
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.
