Recently, a popular line of research in face recognition is adopting margins in the well-established softmax loss function to maximize class separability. In this paper, we first introduce an Additive Angular Margin Loss (ArcFace), which not only has a clear geometric interpretation but also significantly enhances the discriminative power. Since ArcFace is susceptible to the massive label noise, we further propose sub-center ArcFace, in which each class contains K sub-centers and training samples only need to be close to any of the K positive sub-centers. Sub-center ArcFace encourages one dominant sub-class that contains the majority of clean faces and non-dominant sub-classes that include hard or noisy faces. Based on this self-propelled isolation, we boost the performance through automatically purifying raw web faces under massive real-world noise. Besides discriminative feature embedding, we also explore the inverse problem, mapping feature vectors to face images. Without training any additional generator or discriminator, the pre-trained ArcFace model can generate identity-preserved face images for both subjects inside and outside the training data only by using the network gradient and Batch Normalization (BN) priors. Extensive experiments demonstrate that ArcFace can enhance the discriminative feature embedding as well as strengthen the generative face synthesis.

Recent years witnessed the breakthrough of face recognition with deep convolutional neural networks. Dozens of papers in the field of FR are published every year. Some of them were applied in the industrial community and played an important role in human life such as device unlock, mobile payment, and so on. This paper provides an introduction to face recognition, including its history, pipeline, algorithms based on conventional manually designed features or deep learning, mainstream training, evaluation datasets, and related applications. We have analyzed and compared state-of-the-art works as many as possible, and also carefully designed a set of experiments to find the effect of backbone size and data distribution. This survey is a material of the tutorial named The Practical Face Recognition Technology in the Industrial World in the FG2023.

基于软马克斯的损失函数及其变体（例如，界面，圆顶和弧形）可显着改善野生无约束场景中的面部识别性能。这些算法的一种常见实践是对嵌入特征和线性转换矩阵之间的乘法进行优化。但是，在大多数情况下，基于传统的设计经验给出了嵌入功能的尺寸，并且在给出固定尺寸时，使用该功能本身提高性能的研究较少。为了应对这一挑战，本文提出了一种称为subface的软关系近似方法，该方法采用了子空间功能来促进面部识别的性能。具体而言，我们在训练过程中动态选择每个批次中的非重叠子空间特征，然后使用子空间特征在基于软磁性的损失之间近似完整功能，因此，深层模型的可区分性可以显着增强，以增强面部识别。在基准数据集上进行的综合实验表明，我们的方法可以显着提高香草CNN基线的性能，这强烈证明了基于利润率的损失的子空间策略的有效性。

学习歧视性面部特征在建立高性能面部识别模型方面发挥着重要作用。最近的最先进的面部识别解决方案，提出了一种在常用的分类损失函数，Softmax损失中纳入固定的惩罚率，通过最大限度地减少级别的变化来增加面部识别模型的辨别力并最大化级别的帧间变化。边缘惩罚Softmax损失，如arcFace和Cosface，假设可以使用固定的惩罚余量同样地学习不同身份之间的测地距。然而，这种学习目标对于具有不一致的间帧内变化的真实数据并不是现实的，这可能限制了面部识别模型的判别和概括性。在本文中，我们通过提出弹性罚款损失（弹性面）来放松固定的罚款边缘约束，这允许在推动阶级可分离性中灵活性。主要思想是利用从每个训练迭代中的正常分布中汲取的随机保证金值。这旨在提供决策边界机会，以提取和缩回，以允许灵活的类别可分离学习的空间。我们展示了在大量主流基准上使用相同的几何变换，展示了我们的弹性面损失和COSFace损失的优势。从更广泛的角度来看，我们的弹性面在九个主流基准中提出了最先进的面部识别性能。

Face recognition has made extraordinary progress owing to the advancement of deep convolutional neural networks (CNNs). The central task of face recognition, including face verification and identification, involves face feature discrimination. However, the traditional softmax loss of deep CNNs usually lacks the power of discrimination. To address this problem, recently several loss functions such as center loss, large margin softmax loss, and angular softmax loss have been proposed. All these improved losses share the same idea: maximizing inter-class variance and minimizing intra-class variance. In this paper, we propose a novel loss function, namely large margin cosine loss (LMCL), to realize this idea from a different perspective. More specifically, we reformulate the softmax loss as a cosine loss by L 2 normalizing both features and weight vectors to remove radial variations, based on which a cosine margin term is introduced to further maximize the decision margin in the angular space. As a result, minimum intra-class variance and maximum inter-class variance are achieved by virtue of normalization and cosine decision margin maximization. We refer to our model trained with LMCL as CosFace. Extensive experimental evaluations are conducted on the most popular public-domain face recognition datasets such as MegaFace Challenge, Youtube Faces (YTF) and Labeled Face in the Wild (LFW). We achieve the state-of-the-art performance on these benchmarks, which confirms the effectiveness of our proposed approach.

This paper addresses deep face recognition (FR) problem under open-set protocol, where ideal face features are expected to have smaller maximal intra-class distance than minimal inter-class distance under a suitably chosen metric space. However, few existing algorithms can effectively achieve this criterion. To this end, we propose the angular softmax (A-Softmax) loss that enables convolutional neural networks (CNNs) to learn angularly discriminative features. Geometrically, A-Softmax loss can be viewed as imposing discriminative constraints on a hypersphere manifold, which intrinsically matches the prior that faces also lie on a manifold. Moreover, the size of angular margin can be quantitatively adjusted by a parameter m. We further derive specific m to approximate the ideal feature criterion. Extensive analysis and experiments on Labeled Face in the Wild (LFW), Youtube Faces (YTF) and MegaFace Challenge show the superiority of A-Softmax loss in FR tasks. The code has also been made publicly available 1 .

随着最近深度卷积神经网络的进步，一般面临的概念取得了重大进展。然而，最先进的一般面部识别模型对遮挡面部图像没有概括，这正是现实世界场景中的常见情况。潜在原因是用于训练和特定设计的大规模遮挡面部数据，用于解决闭塞所带来的损坏功能。本文提出了一种新颖的面部识别方法，其基于单端到端的深神经网络的闭塞是强大的。我们的方法（使用遮挡掩码）命名（面部识别），学会发现深度卷积神经网络的损坏功能，并通过动态学习的面具清洁它们。此外，我们构建了大规模的遮挡面部图像，从有效且有效地培训。与现有方法相比，依靠外部探测器发现遮挡或采用较少鉴别的浅模型的现有方法，从简单且功能强大。 LFW，Megaface挑战1，RMF2，AR数据集和其他模拟遮挡/掩蔽数据集的实验结果证实，从大幅提高了遮挡下的准确性，并概括了一般面部识别。

横梁面部识别（CFR）旨在识别个体，其中比较面部图像源自不同的感测模式，例如红外与可见的。虽然CFR由于与模态差距相关的面部外观的显着变化，但CFR具有比经典的面部识别更具挑战性，但它在具有有限或挑战的照明的场景中，以及在呈现攻击的情况下，它是优越的。与卷积神经网络（CNNS）相关的人工智能最近的进展使CFR的显着性能提高了。由此激励，这项调查的贡献是三倍。我们提供CFR的概述，目标是通过首先正式化CFR然后呈现具体相关的应用来比较不同光谱中捕获的面部图像。其次，我们探索合适的谱带进行识别和讨论最近的CFR方法，重点放在神经网络上。特别是，我们提出了提取和比较异构特征以及数据集的重新访问技术。我们枚举不同光谱和相关算法的优势和局限性。最后，我们讨论了研究挑战和未来的研究线。

Person re-identification (Re-ID) aims at retrieving a person of interest across multiple non-overlapping cameras. With the advancement of deep neural networks and increasing demand of intelligent video surveillance, it has gained significantly increased interest in the computer vision community. By dissecting the involved components in developing a person Re-ID system, we categorize it into the closed-world and open-world settings. The widely studied closed-world setting is usually applied under various research-oriented assumptions, and has achieved inspiring success using deep learning techniques on a number of datasets. We first conduct a comprehensive overview with in-depth analysis for closed-world person Re-ID from three different perspectives, including deep feature representation learning, deep metric learning and ranking optimization. With the performance saturation under closed-world setting, the research focus for person Re-ID has recently shifted to the open-world setting, facing more challenging issues. This setting is closer to practical applications under specific scenarios. We summarize the open-world Re-ID in terms of five different aspects. By analyzing the advantages of existing methods, we design a powerful AGW baseline, achieving state-of-the-art or at least comparable performance on twelve datasets for FOUR different Re-ID tasks. Meanwhile, we introduce a new evaluation metric (mINP) for person Re-ID, indicating the cost for finding all the correct matches, which provides an additional criteria to evaluate the Re-ID system for real applications. Finally, some important yet under-investigated open issues are discussed.

从大规模嘈杂的面孔中学习强大的特征表示是高性能面部识别的关键挑战之一。最近通过减轻了阶层内冲突和阶级冲突来应对这一挑战。但是，每种冲突中无约束的噪声类型仍然使这些算法难以表现良好。为了更好地理解这一点，我们将每个类别的噪声类型以更细粒度的方式重新制定为n-身份| k^c-clusters。可以通过调整\ nkc的值来生成不同类型的嘈杂面。基于这种统一的公式，我们发现噪声射击表示学习背后的主要障碍是在不同的N，K和C下算法的灵活性。对于此潜在问题，我们提出了一种新方法，称为Evolving子中心学习〜（ESL），找到最佳的超平面，以准确描述大型嘈杂面的潜在空间。更具体地说，我们将每个类的M子中心初始化，ESL鼓励它通过生产，合并和丢弃操作自动与n-身份| k^c-clusters面对面。嘈杂面上属于相同身份的图像可以有效地收敛到同一子中心，并且具有不同身份的样本将被推开。我们通过对具有不同n，k和C的合成噪声数据集进行了精心的消融研究来检查其有效性

分解表示形式通常被用于年龄不变的面部识别（AIFR）任务。但是，这些方法已经达到了一些局限性，（1）具有年龄标签的大规模面部识别（FR）培训数据的要求，这在实践中受到限制； （2）高性能的重型深网架构； （3）他们的评估通常是在与年龄相关的面部数据库上进行的，同时忽略了标准的大规模FR数据库以确保鲁棒性。这项工作提出了一种新颖的轻巧的角度蒸馏（LIAAD）方法，用于克服这些限制的大规模轻量级AIFR。鉴于两个具有不同专业知识的教师，LIAAD引入了学习范式，以有效地提炼老年人的专注和棱角分明的知识，从这些老师到轻量级的学生网络，使其更强大，以更高的fr准确性和稳健的年龄，从而有效地提炼了一个学习范式因素。因此，LIAAD方法能够采用带有和不具有年龄标签的两个FR数据集的优势来训练AIFR模型。除了先前的蒸馏方法主要关注封闭设置问题中的准确性和压缩比，我们的LIAAD旨在解决开放式问题，即大规模的面部识别。对LFW，IJB-B和IJB-C Janus，AgeDB和Megaface-Fgnet的评估证明了拟议方法在轻重量结构上的效率。这项工作还提出了一个新的纵向面部衰老（Logiface）数据库\ footNote {将提供该数据库}，以进一步研究未来与年龄相关的面部问题。

Person re-identification is a challenging task because of the high intra-class variance induced by the unrestricted nuisance factors of variations such as pose, illumination, viewpoint, background, and sensor noise. Recent approaches postulate that powerful architectures have the capacity to learn feature representations invariant to nuisance factors, by training them with losses that minimize intra-class variance and maximize inter-class separation, without modeling nuisance factors explicitly. The dominant approaches use either a discriminative loss with margin, like the softmax loss with the additive angular margin, or a metric learning loss, like the triplet loss with batch hard mining of triplets. Since the softmax imposes feature normalization, it limits the gradient flow supervising the feature embedding. We address this by joining the losses and leveraging the triplet loss as a proxy for the missing gradients. We further improve invariance to nuisance factors by adding the discriminative task of predicting attributes. Our extensive evaluation highlights that when only a holistic representation is learned, we consistently outperform the state-of-the-art on the three most challenging datasets. Such representations are easier to deploy in practical systems. Finally, we found that joining the losses removes the requirement for having a margin in the softmax loss while increasing performance.

In this paper, we propose a conceptually simple and geometrically interpretable objective function, i.e. additive margin Softmax (AM-Softmax), for deep face verification. In general, the face verification task can be viewed as a metric learning problem, so learning large-margin face features whose intra-class variation is small and inter-class difference is large is of great importance in order to achieve good performance. Recently, Large-margin Softmax [10] and Angular Softmax [9] have been proposed to incorporate the angular margin in a multiplicative manner. In this work, we introduce a novel additive angular margin for the Softmax loss, which is intuitively appealing and more interpretable than the existing works. We also emphasize and discuss the importance of feature normalization in the paper. Most importantly, our experiments on LFW and MegaFace show that our additive margin softmax loss consistently performs better than the current state-of-the-art methods using the same network architecture and training dataset. Our code has also been made available 1 .

Person recognition at a distance entails recognizing the identity of an individual appearing in images or videos collected by long-range imaging systems such as drones or surveillance cameras. Despite recent advances in deep convolutional neural networks (DCNNs), this remains challenging. Images or videos collected by long-range cameras often suffer from atmospheric turbulence, blur, low-resolution, unconstrained poses, and poor illumination. In this paper, we provide a brief survey of recent advances in person recognition at a distance. In particular, we review recent work in multi-spectral face verification, person re-identification, and gait-based analysis techniques. Furthermore, we discuss the merits and drawbacks of existing approaches and identify important, yet under explored challenges for deploying remote person recognition systems in-the-wild.

图像分辨率或一般图像质量在当今面部识别系统的性能中起着至关重要的作用。为了解决这个问题，我们提出了一种流行的三胞胎损失的新型组合，以通过微调现有面部识别模型来提高与图像分辨率的鲁棒性。随着八度损失，我们利用高分辨率图像及其合成下采样变体之间的关系与其身份标签共同采样。通过我们的方法对几种最先进的方法进行微调证明，我们可以在各种数据集上显着提高跨分辨率（高低分辨率）面部验证的性能，而不会有意义地加剧高高度的性能分辨率图像。我们的方法应用于FaceTransFormer网络，在挑战性的XQLFW数据集上达到95.12％的面对验证精度，同时在LFW数据库上达到99.73％。此外，低到低面验证精度从我们的方法中受益。我们发布我们的代码，以允许将OCTUPLET损失的无缝集成到现有框架中。

随着近期神经网络的成功，对人脸识别取得了显着进展。然而，收集面部识别的大规模现实世界培训数据已经挑战，特别是由于标签噪音和隐私问题。同时，通常从网络图像收集现有的面部识别数据集，缺乏关于属性的详细注释（例如，姿势和表达），因此对面部识别的不同属性的影响已经很差。在本文中，我们使用合成面部图像，即Synface来解决面部识别中的上述问题。具体而言，我们首先探讨用合成和真实面部图像训练的最近最先进的人脸识别模型之间的性能差距。然后，我们分析了性能差距背后的潜在原因，例如，较差的阶级变化和合成和真实面部图像之间的域间隙。灵感来自于此，我们使用身份混合（IM）和域混合（DM）设计了SYNFACE，以减轻上述性能差距，展示了对面部识别的综合数据的巨大潜力。此外，利用可控的面部合成模型，我们可以容易地管理合成面代的不同因素，包括姿势，表达，照明，身份的数量和每个身份的样本。因此，我们还对综合性面部图像进行系统实证分析，以提供一些关于如何有效利用综合数据进行人脸识别的见解。

近年来，由于深度学习体系结构的有希望的进步，面部识别系统取得了非凡的成功。但是，当将配置图像与额叶图像的画廊匹配时，它们仍然无法实现预期的准确性。当前方法要么执行姿势归一化（即额叶化）或脱离姿势信息以进行面部识别。相反，我们提出了一种新方法，通过注意机制将姿势用作辅助信息。在本文中，我们假设使用注意机制姿势参加的信息可以指导剖面面上的上下文和独特的特征提取，从而进一步使嵌入式域中的更好表示形式学习。为了实现这一目标，首先，我们设计了一个统一的耦合曲线到额定面部识别网络。它通过特定于类的对比损失来学习从面孔到紧凑的嵌入子空间的映射。其次，我们开发了一个新颖的姿势注意力块（PAB），以专门指导从剖面面上提取姿势 - 不合稳定的特征。更具体地说，PAB旨在显式地帮助网络沿着频道和空间维度沿着频道和空间维度的重要特征，同时学习嵌入式子空间中的歧视性但构成不变的特征。为了验证我们提出的方法的有效性，我们对包括多PIE，CFP，IJBC在内的受控和野生基准进行实验，并在艺术状态下表现出优势。

面部图像的质量显着影响底层识别算法的性能。面部图像质量评估（FIQA）估计捕获的图像的效用在实现可靠和准确的识别性能方面。在这项工作中，我们提出了一种新的学习范式，可以在培训过程中学习内部网络观察。基于此，我们所提出的CR-FiQA使用该范例来通过预测其相对分类性来估计样品的面部图像质量。基于关于其类中心和最近的负类中心的角度空间中的训练样本特征表示来测量该分类性。我们通过实验说明了面部图像质量与样本相对分类性之间的相关性。由于此类属性仅为培训数据集可观察到，因此我们建议从培训数据集中学习此属性，并利用它来预测看不见样品的质量措施。该培训同时执行，同时通过用于面部识别模型训练的角度裕度罚款的软墨损失来优化类中心。通过对八个基准和四个面部识别模型的广泛评估实验，我们展示了我们提出的CR-FiQA在最先进（SOTA）FIQ算法上的优越性。

在本文中，我们试图在抽象嵌入空间中绘制额叶和轮廓面图像之间的连接。我们使用耦合编码器网络利用此连接将额叶/配置文件的面部图像投影到一个常见的潜在嵌入空间中。提出的模型通过最大化面部两种视图之间的相互信息来迫使嵌入空间中表示的相似性。拟议的耦合编码器从三个贡献中受益于与极端姿势差异的匹配面。首先，我们利用我们的姿势意识到的对比学习来最大程度地提高身份额叶和概况表示之间的相互信息。其次，由在过去的迭代中积累的潜在表示组成的内存缓冲区已集成到模型中，因此它可以比小批量大小相对较多的实例。第三，一种新颖的姿势感知的对抗结构域适应方法迫使模型学习从轮廓到额叶表示的不对称映射。在我们的框架中，耦合编码器学会了扩大真实面孔和冒名顶替面部分布之间的边距，这导致了相同身份的不同观点之间的高度相互信息。通过对四个基准数据集的广泛实验，评估和消融研究来研究拟议模型的有效性，并与引人入胜的最新算法进行比较。

面部识别系统必须处理可能导致匹配决策不正确的大型变量（例如不同的姿势，照明和表达）。这些可变性可以根据面部图像质量来测量，这在样本的效用上定义了用于识别的实用性。以前的识别作品不使用这种有价值的信息或利用非本质上的质量估算。在这项工作中，我们提出了一种简单且有效的面部识别解决方案（Qmagface），其将质量感知的比较分数与基于大小感知角裕度损耗的识别模型相结合。所提出的方法包括比较过程中特定于模型的面部图像质量，以增强在无约束情况下的识别性能。利用利用损失诱导的质量与其比较评分之间的线性，我们的质量意识比较功能简单且高度普遍。在几个面部识别数据库和基准上进行的实验表明，引入的质量意识导致识别性能一致的改进。此外，所提出的Qmagface方法在挑战性环境下特别好，例如交叉姿势，跨年或跨品。因此，它导致最先进的性能在几个面部识别基准上，例如在XQLFQ上的98.50％，83.97％，CFP-FP上的98.74％。 QMagface的代码是公开可用的。