在本文中,我们分析了面部图像中基本身份的基本3D形状如何扭曲其整体外观,尤其是从深面识别的角度来看。正如在流行的训练数据增强方案中所做的那样,我们以随机选择或最合适的3D面部模型的形式渲染真实和合成的面部图像,以产生基本身份的新视图。我们比较了这些图像产生的深度特征,以评估这些渲染引入原始身份的扰动。我们以各种程度的面部偏航进行了这种分析,基本身份的性别和种族各不相同。此外,我们调查在这些渲染图像中添加某种形式的上下文和背景像素,当用作训练数据时,进一步改善了面部识别模型的下游性能。我们的实验证明了面部形状在准确的面部匹配中的重要性,并基于上下文数据对网络训练的重要性。
translated by 谷歌翻译
深度神经网络在人类分析中已经普遍存在,增强了应用的性能,例如生物识别识别,动作识别以及人重新识别。但是,此类网络的性能通过可用的培训数据缩放。在人类分析中,对大规模数据集的需求构成了严重的挑战,因为数据收集乏味,廉价,昂贵,并且必须遵守数据保护法。当前的研究研究了\ textit {合成数据}的生成,作为在现场收集真实数据的有效且具有隐私性的替代方案。这项调查介绍了基本定义和方法,在生成和采用合成数据进行人类分析时必不可少。我们进行了一项调查,总结了当前的最新方法以及使用合成数据的主要好处。我们还提供了公开可用的合成数据集和生成模型的概述。最后,我们讨论了该领域的局限性以及开放研究问题。这项调查旨在为人类分析领域的研究人员和从业人员提供。
translated by 谷歌翻译
In this paper, we introduce a new large-scale face dataset named VGGFace2. The dataset contains 3.31 million images of 9131 subjects, with an average of 362.6 images for each subject. Images are downloaded from Google Image Search and have large variations in pose, age, illumination, ethnicity and profession (e.g. actors, athletes, politicians).The dataset was collected with three goals in mind: (i) to have both a large number of identities and also a large number of images for each identity; (ii) to cover a large range of pose, age and ethnicity; and (iii) to minimise the label noise. We describe how the dataset was collected, in particular the automated and manual filtering stages to ensure a high accuracy for the images of each identity.To assess face recognition performance using the new dataset, we train ResNet-50 (with and without Squeeze-and-Excitation blocks) Convolutional Neural Networks on VG-GFace2, on MS-Celeb-1M, and on their union, and show that training on VGGFace2 leads to improved recognition performance over pose and age. Finally, using the models trained on these datasets, we demonstrate state-of-the-art performance on the face recognition of IJB datasets, exceeding the previous state-of-the-art by a large margin. The dataset and models are publicly available 1 .
translated by 谷歌翻译
媒体报道指责人们对“偏见”',“”性别歧视“和”种族主义“的人士指责。研究文献中有共识,面部识别准确性为女性较低,妇女通常具有更高的假匹配率和更高的假非匹配率。然而,几乎没有出版的研究,旨在识别女性准确性较低的原因。例如,2019年的面部识别供应商测试将在广泛的算法和数据集中记录较低的女性准确性,并且数据集也列出了“分析原因和效果”在“我们没有做的东西”下''。我们介绍了第一个实验分析,以确定在去以前研究的数据集上对女性的较低人脸识别准确性的主要原因。在测试图像中控制相等的可见面部可见面积减轻了女性的表观更高的假非匹配率。其他分析表明,化妆平衡数据集进一步改善了女性以实现较低的虚假非匹配率。最后,聚类实验表明,两种不同女性的图像本质上比两种不同的男性更相似,潜在地占错误匹配速率的差异。
translated by 谷歌翻译
The emergence of COVID-19 has had a global and profound impact, not only on society as a whole, but also on the lives of individuals. Various prevention measures were introduced around the world to limit the transmission of the disease, including face masks, mandates for social distancing and regular disinfection in public spaces, and the use of screening applications. These developments also triggered the need for novel and improved computer vision techniques capable of (i) providing support to the prevention measures through an automated analysis of visual data, on the one hand, and (ii) facilitating normal operation of existing vision-based services, such as biometric authentication schemes, on the other. Especially important here, are computer vision techniques that focus on the analysis of people and faces in visual data and have been affected the most by the partial occlusions introduced by the mandates for facial masks. Such computer vision based human analysis techniques include face and face-mask detection approaches, face recognition techniques, crowd counting solutions, age and expression estimation procedures, models for detecting face-hand interactions and many others, and have seen considerable attention over recent years. The goal of this survey is to provide an introduction to the problems induced by COVID-19 into such research and to present a comprehensive review of the work done in the computer vision based human analysis field. Particular attention is paid to the impact of facial masks on the performance of various methods and recent solutions to mitigate this problem. Additionally, a detailed review of existing datasets useful for the development and evaluation of methods for COVID-19 related applications is also provided. Finally, to help advance the field further, a discussion on the main open challenges and future research direction is given.
translated by 谷歌翻译
面部合成的进步已经提出了关于合成面的欺骗性使用的警报。合成综合性可以有效地用于欺骗人类观察者吗?在本文中,我们介绍了使用不同策略产生的合成面的人类感知的研究,包括基于最先进的深学的GaN模型。这是第一次严格研究从心理学的实验技术接地的合成面代发电技术的有效性研究。我们回答了重要的问题,如GaN的频率和更传统的图像处理的技术混淆人类观察者,并且在综合性脸部图像中有细微的线索,导致人类将其视为假冒,而无需寻找明显的线索还为了回答这些问题,我们进行了一系列大规模众群行为实验,具有不同的面膜。结果表明,人类无法在几个不同的情况下区分真实面的合成面。这一发现对面部图像呈现给人类用户的许多不同应用具有严重影响。
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
深度学习的高级面部识别以实现前所未有的准确性。但是,了解面部的本地部分如何影响整体识别性能仍然不清楚。除其他外,面部掉期已经进行了实验,但只是为了整个脸。在本文中,我们建议交换面部零件,以剥夺不同面部零件(例如眼睛,鼻子和嘴巴)的识别相关性。在我们的方法中,通过拟合3D先验来交换从源面转换为目标的零件,该零件在零件之间建立密集的像素对应关系,同时还要处理姿势差异。然后,无缝克隆用于在映射的源区域和目标面的形状和肤色之间获得平滑的过渡。我们设计了一个实验协议,该协议使我们能够在通过深网进行分类时得出一些初步结论,表明眼睛和眉毛区域的突出性。可在https://github.com/clferrari/facepartsswap上找到代码
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
自动面部识别是一个知名的研究领域。在该领域的最后三十年的深入研究中,已经提出了许多不同的面部识别算法。随着深度学习的普及及其解决各种不同问题的能力,面部识别研究人员集中精力在此范式下创建更好的模型。从2015年开始,最先进的面部识别就植根于深度学习模型。尽管有大规模和多样化的数据集可用于评估面部识别算法的性能,但许多现代数据集仅结合了影响面部识别的不同因素,例如面部姿势,遮挡,照明,面部表情和图像质量。当算法在这些数据集上产生错误时,尚不清楚哪些因素导致了此错误,因此,没有指导需要多个方向进行更多的研究。这项工作是我们以前在2014年开发的作品的后续作品,最终于2016年发表,显示了各种面部方面对面部识别算法的影响。通过将当前的最新技术与过去的最佳系统进行比较,我们证明了在强烈的遮挡下,某些类型的照明和强烈表达的面孔是深入学习算法所掌握的问题,而具有低分辨率图像的识别,极端的姿势变化和开放式识别仍然是一个开放的问题。为了证明这一点,我们使用六个不同的数据集和五种不同的面部识别算法以开源和可重现的方式运行一系列实验。我们提供了运行所有实验的源代码,这很容易扩展,因此在我们的评估中利用自己的深网只有几分钟的路程。
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
面部3D形态模型是无数应用程序的主要计算机视觉主题,并且在过去二十年中已得到高度优化。深层生成网络的巨大改进创造了改善此类模型的各种可能性,并引起了广泛的兴趣。此外,神经辐射领域的最新进展正在彻底改变已知场景的新颖视图综合。在这项工作中,我们提出了一个面部3D形态模型,该模型利用了上述两者,并且可以准确地对受试者的身份,姿势和表达进行建模,并以任意照明形式呈现。这是通过利用强大的基于风格的发电机来克服神经辐射场的两个主要弱点,即它们的刚度和渲染速度来实现的。我们介绍了一个基于样式的生成网络,该网络在一个通过中综合了全部,并且仅在神经辐射场的所需渲染样品中构成。我们创建了一个庞大的标记为面部渲染的合成数据集,并在这些数据上训练网络,以便它可以准确地建模并推广到面部身份,姿势和外观。最后,我们表明该模型可以准确地适合“野外”的任意姿势和照明的面部图像,提取面部特征,并用于在可控条件下重新呈现面部。
translated by 谷歌翻译
Privacy of machine learning models is one of the remaining challenges that hinder the broad adoption of Artificial Intelligent (AI). This paper considers this problem in the context of image datasets containing faces. Anonymization of such datasets is becoming increasingly important due to their central role in the training of autonomous cars, for example, and the vast amount of data generated by surveillance systems. While most prior work de-identifies facial images by modifying identity features in pixel space, we instead project the image onto the latent space of a Generative Adversarial Network (GAN) model, find the features that provide the biggest identity disentanglement, and then manipulate these features in latent space, pixel space, or both. The main contribution of the paper is the design of a feature-preserving anonymization framework, StyleID, which protects the individuals' identity, while preserving as many characteristics of the original faces in the image dataset as possible. As part of the contribution, we present a novel disentanglement metric, three complementing disentanglement methods, and new insights into identity disentanglement. StyleID provides tunable privacy, has low computational complexity, and is shown to outperform current state-of-the-art solutions.
translated by 谷歌翻译
随着面部生物识别技术的广泛采用,在自动面部识别(FR)应用中区分相同的双胞胎和非双胞胎外观相似的问题变得越来越重要。由于同卵双胞胎和外观相似的面部相似性很高,因此这些面对对面部识别工具表示最困难的病例。这项工作介绍了迄今为止汇编的最大的双胞胎数据集之一,以应对两个挑战:1)确定相同双胞胎和2)的面部相似性的基线度量和2)应用此相似性措施来确定多ppelgangers的影响或外观 - Alikes,关于大面部数据集的FR性能。面部相似性度量是通过深度卷积神经网络确定的。该网络经过量身定制的验证任务进行培训,旨在鼓励网络在嵌入空间中将高度相似的面对对组合在一起,并达到0.9799的测试AUC。所提出的网络为任何两个给定的面提供了定量相似性评分,并已应用于大规模面部数据集以识别相似的面对对。还执行了一个附加分析,该分析还将面部识别工具返回的比较分数以及提议网络返回的相似性分数。
translated by 谷歌翻译
广泛认为,面部识别准确性存在“性别差距”,女性具有较高的错误匹配和错误的非匹配率。但是,关于这种性别差距的原因,相对较少了解。甚至最近有关人口影响的NIST报告也列出了“我们没有做的事情”下的“分析因果”。我们首先证明女性和男性发型具有影响面部识别准确性的重要差异。特别是,与女性相比,男性面部毛发有助于在不同男性面孔之间产生更大的外观平均差异。然后,我们证明,当用来估计识别精度的数据在性别之间保持平衡,以使发型如何阻塞面部时,最初观察到的性别差距在准确性上大大消失。我们为两个不同的匹配者展示了这一结果,并分析了白种人和非裔美国人的图像。这些结果表明,对准确性的人口统计学差异的未来研究应包括检查测试数据的平衡质量,作为问题制定的一部分。为了促进可重复的研究,将公开使用此研究中使用的匹配项,属性分类器和数据集。
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
社会存在,与真实的人在一起的感觉,将推动由数字人类在虚拟现实(VR)中驱动的下一代通信系统。最佳的3D视频VR化身最小化不可思议的效果取决于特定于人的模型。但是,这些PS模型既耗时又耗时,并且通常受到数据可变性有限的训练,从而导致概括和稳健性差。影响面部表达转移算法准确性的主要变异性包括使用不同的VR耳机(例如,摄像头配置,耳机的斜率),面部外观随时间变化(例如,胡须,化妆)和环境因素(例如, ,照明,背景)。这是VR中这些模型可扩展性的主要缺点。本文通过提出了通过专门的增强策略培训的端到端多个认同体系结构(MIA)来克服这些局限性的进展。 MIA使用最小的个性化信息(即中性的3D网格形状),从VR耳机中的三个相机(两只眼睛,一只嘴)从三个相机(两只眼睛,一只嘴)驱动了头像的形状。同样,如果可用PS纹理解码器,MIA能够在具有挑战性的情况下驱动完整的Avatar(Shape+Texture)强劲的PS模型。我们对改善鲁棒性和概括的关键贡献是,我们的方法以无监督的方式隐含地将面部表达与滋扰因素(例如耳机,环境,面部外观)脱离。我们在各种实验中证明了所提出的方法与最先进的PS方法的卓越性能和鲁棒性。
translated by 谷歌翻译
当前用于面部识别的模型(FR)中存在人口偏见。我们在野外(BFW)数据集中平衡的面孔是衡量种族和性别亚组偏见的代理,使一个人可以表征每个亚组的FR表现。当单个分数阈值确定样本对是真实还是冒名顶替者时,我们显示的结果是非最佳选择的。在亚组中,性能通常与全球平均水平有很大差异。因此,仅适用于与验证数据相匹配的人群的特定错误率。我们使用新的域适应性学习方案来减轻性能不平衡,以使用最先进的神经网络提取的面部特征。该技术平衡了性能,但也可以提高整体性能。该建议的好处是在面部特征中保留身份信息,同时减少其所包含的人口统计信息。人口统计学知识的去除阻止了潜在的未来偏见被注入决策。由于对个人的可用信息或推断,因此此删除可改善隐私。我们定性地探索这一点;我们还定量地表明,亚组分类器不再从提出的域适应方案的特征中学习。有关源代码和数据描述,请参见https://github.com/visionjo/facerec-bias-bfw。
translated by 谷歌翻译
Several face de-identification methods have been proposed to preserve users' privacy by obscuring their faces. These methods, however, can degrade the quality of photos, and they usually do not preserve the utility of faces, e.g., their age, gender, pose, and facial expression. Recently, advanced generative adversarial network models, such as StyleGAN, have been proposed, which generate realistic, high-quality imaginary faces. In this paper, we investigate the use of StyleGAN in generating de-identified faces through style mixing, where the styles or features of the target face and an auxiliary face get mixed to generate a de-identified face that carries the utilities of the target face. We examined this de-identification method with respect to preserving utility and privacy, by implementing several face detection, verification, and identification attacks. Through extensive experiments and also comparing with two state-of-the-art face de-identification methods, we show that StyleGAN preserves the quality and utility of the faces much better than the other approaches and also by choosing the style mixing levels correctly, it can preserve the privacy of the faces much better than other methods.
translated by 谷歌翻译
深度学习系统needlargedatafortraining.Datasets的面部验证系统难以获得并容易出现隐私问题。由GAN等生成模型生成的合成数据可以是一个很好的选择。但是,我们表明,甘恩产生的数据容易出现偏见和公平问题。特别是在FFHQ数据集中训练的甘斯表明,在20-29岁年龄段的年龄组中产生白脸。我们还证明,当用于微调面部验证系统时,合成面部面孔会引起不同的影响,特别是针对种族属性的影响。这是使用$ dob_ {fv} $ metric测量的,该公制定义为gar@far far for face验证的标准偏差。
translated by 谷歌翻译