NIR到VIS的面部识别是通过提取域不变特征来识别两个不同域的面。但是,由于两个不同的领域特征以及缺乏NIR FACE数据集,这是一个具有挑战性的问题。为了在使用现有面部识别模型时减少域差异,我们提出了一个“关系模块”,它可以简单地添加到任何面部识别模型中。从面部图像中提取的本地功能包含面部每个组件的信息。基于两个不同的域特征,使用本地特征之间的关系比以原样的方式使用它更具域名。除了这些关系外,位置信息,例如从嘴唇到下巴到眼睛到眼睛到眼睛的距离,还提供域不变的信息。在我们的关系模块中,关系层隐含地捕获关系,并协调层对位置信息进行建模。此外,我们提出的三重态损失和有条件的边缘损失减少了训练中类内部的变化,并导致了进一步的改进。与一般面部识别模型不同,我们的附加模块无需使用大型数据集进行预训练。所提出的模块仅使用CASIA NIR-VIS 2.0数据库进行微调。使用拟议的模块,我们达到了14.81%的排名1精度和15.47%的验证率,为0.1%的验证率与两个基线模型相比。
translated by 谷歌翻译
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。
translated by 谷歌翻译
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.
translated by 谷歌翻译
长期以来,面部识别一直是人工智能领域的一个积极研究领域,尤其是自近年来深度学习的兴起以来。在某些实际情况下,每个身份只有一个可以培训的样本。在这种情况下的面部识别被称为单个样本识别,并对深层模型的有效培训构成了重大挑战。因此,近年来,研究人员试图释放更多的深度学习潜力,并在单个样本情况下提高模型识别性能。尽管已经对传统的单个样本面部识别方法进行了几项全面的调查,但这些评论很少涉及新兴的基于深度学习的方法。因此,我们将重点放在本文中的基于深度学习的方法上,将其分类为虚拟示例方法和通用学习方法。在前一种类别中,生成虚拟图像或虚拟特征以使深层模型的训练受益。在后者中,使用了其他多样本通用集。通用学习方法有三种类型:结合传统方法和深度特征,改善损失功能并改善网络结构,所有这些都涵盖了我们的分析。此外,我们回顾了通常用于评估单个样本面部识别模型的面部数据集,并继续比较不同类型的模型的结果。此外,我们讨论了现有的单个样本面部识别方法的问题,包括虚拟样本方法中的身份信息保存,通用学习方法中的域适应性。此外,我们认为开发无监督的方法是一个有希望的未来方向,并指出语义差距是需要进一步考虑的重要问题。
translated by 谷歌翻译
可见光面图像匹配是跨模型识别的具有挑战性的变化。挑战在于,可见和热模式之间的较大的模态间隙和低相关性。现有方法采用图像预处理,特征提取或常见的子空间投影,它们本身是独立的问题。在本文中,我们提出了一种用于交叉模态面部识别的端到端框架。该算法的旨在从未处理的面部图像学习身份鉴别特征,并识别跨模态图像对。提出了一种新颖的单元级丢失,用于在丢弃模态信息时保留身份信息。另外,提出用于将图像对分类能力集成到网络中的跨模判位块。所提出的网络可用于提取无关的矢量表示或测试图像的匹配对分类。我们对五个独立数据库的跨型号人脸识别实验表明,该方法实现了对现有最先进的方法的显着改善。
translated by 谷歌翻译
异质的面部识别(HFR)旨在匹配不同域(例如,可见到近红外图像)的面孔,该面孔已被广泛应用于身份验证和取证方案。但是,HFR是一个具有挑战性的问题,因为跨域差异很大,异质数据对有限和面部属性变化很大。为了应对这些挑战,我们从异质数据增强的角度提出了一种新的HFR方法,该方法称为面部合成,具有身份 - 属性分解(FSIAD)。首先,身份属性分解(IAD)将图像截取到与身份相关的表示和与身份无关的表示(称为属性)中,然后降低身份和属性之间的相关性。其次,我们设计了一个面部合成模块(FSM),以生成大量具有分离的身份和属性的随机组合的图像,以丰富合成图像的属性多样性。原始图像和合成图像均被用于训练HFR网络,以应对挑战并提高HFR的性能。在五个HFR数据库上进行的广泛实验验证了FSIAD的性能比以前的HFR方法更高。特别是,FSIAD以vr@far = 0.01%在LAMP-HQ上获得了4.8%的改善,这是迄今为止最大的HFR数据库。
translated by 谷歌翻译
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.
translated by 谷歌翻译
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。
translated by 谷歌翻译
学习模态不变功能是可见热跨模板人员重新凝视(VT-REID)问题的核心,其中查询和画廊图像来自不同的模式。现有工作通过使用对抗性学习或仔细设计特征提取模块来隐式地将像素和特征空间中的模态对齐。我们提出了一个简单但有效的框架MMD-REID,通过明确的差异减少约束来降低模态差距。 MMD-REID从最大均值(MMD)中获取灵感,广泛使用的统计工具用于确定两个分布之间的距离。 MMD-REID采用新的基于边缘的配方,以匹配可见和热样品的类条件特征分布,以最大限度地减少级别的距离,同时保持特征辨别性。 MMD-Reid是一个简单的架构和损失制定方面的框架。我们对MMD-REID的有效性进行了广泛的实验,以使MMD-REID对调整边缘和阶级条件分布的有效性,从而学习模型无关和身份的一致特征。所提出的框架显着优于Sysu-MM01和RegDB数据集的最先进的方法。代码将在https://github.com/vcl-iisc/mmd -reid发布
translated by 谷歌翻译
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.
translated by 谷歌翻译
Near infrared (NIR) to Visible (VIS) face matching is challenging due to the significant domain gaps as well as a lack of sufficient data for cross-modality model training. To overcome this problem, we propose a novel method for paired NIR-VIS facial image generation. Specifically, we reconstruct 3D face shape and reflectance from a large 2D facial dataset and introduce a novel method of transforming the VIS reflectance to NIR reflectance. We then use a physically-based renderer to generate a vast, high-resolution and photorealistic dataset consisting of various poses and identities in the NIR and VIS spectra. Moreover, to facilitate the identity feature learning, we propose an IDentity-based Maximum Mean Discrepancy (ID-MMD) loss, which not only reduces the modality gap between NIR and VIS images at the domain level but encourages the network to focus on the identity features instead of facial details, such as poses and accessories. Extensive experiments conducted on four challenging NIR-VIS face recognition benchmarks demonstrate that the proposed method can achieve comparable performance with the state-of-the-art (SOTA) methods without requiring any existing NIR-VIS face recognition datasets. With slightly fine-tuning on the target NIR-VIS face recognition datasets, our method can significantly surpass the SOTA performance. Code and pretrained models are released under the insightface (https://github.com/deepinsight/insightface/tree/master/recognition).
translated by 谷歌翻译
本文从跨模式度量学习的角度来解决基于零点草图的图像检索(ZS-SBIR)问题。此任务具有两个特性:1)零拍摄设置需要具有良好的课堂紧凑性和识别新颖类别的课堂间差异的度量空间,而2)草图查询和照片库是不同的模态。从两个方面,公制学习视点益处ZS-SBIR。首先,它促进了深度度量学习(DML)中最近的良好实践的改进。通过在DML中结合两种基本学习方法,例如分类培训和成对培训,我们为ZS-SBIR设置了一个强大的基线。没有钟声和口哨,这种基线实现了竞争的检索准确性。其次,它提供了一个正确抑制模态间隙至关重要的洞察力。为此,我们设计了一种名为Domency Ippar Triplet硬挖掘(Mathm)的新颖方法。 Mathm增强了基线,具有三种类型的成对学习,例如跨模型样本对,模态样本对,以及它们的组合。\我们还设计了一种自适应加权方法,可以在动态训练期间平衡这三个组件。实验结果证实,Mathm根据强大的基线带来另一轮显着改进,并建立了新的最先进的性能。例如,在Tu-Berlin数据集上,我们达到了47.88 + 2.94%地图@全部和58.28 + 2.34%prip @ 100。代码将在:https://github.com/huangzongheng/mathm公开使用。
translated by 谷歌翻译
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。
translated by 谷歌翻译
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.
translated by 谷歌翻译
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.
translated by 谷歌翻译
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 .
translated by 谷歌翻译
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。
translated by 谷歌翻译
基于草图的3D形状检索是一项具有挑战性的任务,这是由于草图和3D形状之间的较大域差异。由于现有方法是在相同类别上进行培训和评估的,因此他们无法有效地识别培训期间未使用的类别。在本文中,我们建议用于基于零素描的3D检索的新型域分解生成对抗网络(DD-GAN),该域可以检索训练过程中未访问的不看到的类别。具体而言,我们首先通过删除草图和3D形状的学习特征来生成域不变的特征和特定于域特异性特征,在该特征中,域,域,不变的特征用于与相应的单词嵌入在一起。然后,我们开发了一个生成的对抗网络,该网络将所见类别的特定域特征与对齐的域不变特征结合在一起,以合成样品,在其中使用相应的单词嵌入式生成了看不见类别的合成样本。最后,我们使用看不见类别的综合样本与可见类别的真实样本相结合来训练网络进行检索,以便可以识别出看不见的类别。为了减少域移位问题,我们利用未看到的未见样本来增强歧视者的歧视能力。通过鉴别器将生成的样品与未看到的看不见的样品区分开,生成器可以生成更现实的看不见的样品。 SHEREC'13和SHEREC'14数据集的广泛实验表明,我们的方法显着提高了看不见类别的检索性能。
translated by 谷歌翻译
最近的研究表明,明确的深度特征匹配以及大规模和多样化的训练数据都可以显着提高人员重新识别的泛化。然而,在大规模数据上学习深度匹配者的效率尚未得到充分研究。虽然使用分类参数或课程内存是一种流行的方式,但它会引发大的内存和计算成本。相比之下,迷你批量内的成对深度度量学习将是一个更好的选择。然而,最受欢迎的随机采样方法,众所周知的PK采样器,对深度度量学习不是信息性和有效的。虽然在线硬示例挖掘在一定程度上提高了学习效率,但随机采样后迷你批次仍然有限。这激发了我们在数据采样阶段之前探讨了先前使用硬示例挖掘。为此,在本文中,我们提出了一种有效的跨批量采样方法,称为图形采样(GS),用于大规模深度度量学习。基本思想是为每个时代开始的所有类构建最近的邻居关系图。然后,每个迷你批处理由随机选择的类和其最近的邻类组成,以便为学习提供信息和具有挑战性的例子。与适应的竞争性基线一起,我们在更广泛的人中改善了先前的最先进状态,在MAP中最明显重新鉴定,高达24%和13.8%。此外,所提出的方法还优于竞争性基线在地图中排名-1和5.3%的竞争性基线。同时,培训时间明显减少了多达五次,例如五次。在具有8,000个身份的大型数据集中培训12.2小时至2.3小时。代码可在https://github.com/shengcailiao/qaconv获得。
translated by 谷歌翻译
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。
translated by 谷歌翻译