Current domain adaptation methods for face anti-spoofing leverage labeled source domain data and unlabeled target domain data to obtain a promising generalizable decision boundary. However, it is usually difficult for these methods to achieve a perfect domain-invariant liveness feature disentanglement, which may degrade the final classification performance by domain differences in illumination, face category, spoof type, etc. In this work, we tackle cross-scenario face anti-spoofing by proposing a novel domain adaptation method called cyclically disentangled feature translation network (CDFTN). Specifically, CDFTN generates pseudo-labeled samples that possess: 1) source domain-invariant liveness features and 2) target domain-specific content features, which are disentangled through domain adversarial training. A robust classifier is trained based on the synthetic pseudo-labeled images under the supervision of source domain labels. We further extend CDFTN for multi-target domain adaptation by leveraging data from more unlabeled target domains. Extensive experiments on several public datasets demonstrate that our proposed approach significantly outperforms the state of the art.
translated by 谷歌翻译
面部抗泡沫(FAS)旨在将面部欺骗攻击与真实的攻击区分开,通常通过学习适当的模型来执行相关的分类任务。在实践中,人们期望将这种模型推广到不同图像域中的FAS。此外,假设将事先知道欺骗攻击的类型是不切实际的。在本文中,我们提出了一个深度学习模型,以解决上述域名抗繁殖任务。特别是,我们提出的网络能够将面部无性表示与无关的面部表述(即面部内容和图像域特征)相关。所产生的LIVISE表示表现出足够的域不变特性,因此可以应用于执行域将来的FAS。在我们的实验中,我们在具有各种设置的五个基准数据集上进行实验,并验证我们的模型在识别未见图像域中的新型欺骗攻击方面对最新方法的表现有利。
translated by 谷歌翻译
最近,面部生物识别是对传统认证系统的方便替代的巨大关注。因此,检测恶意尝试已经发现具有重要意义,导致面部抗欺骗〜(FAS),即面部呈现攻击检测。与手工制作的功能相反,深度特色学习和技术已经承诺急剧增加FAS系统的准确性,解决了实现这种系统的真实应用的关键挑战。因此,处理更广泛的发展以及准确的模型的新研究区越来越多地引起了研究界和行业的关注。在本文中,我们为自2017年以来对与基于深度特征的FAS方法相关的文献综合调查。在这一主题上阐明,基于各种特征和学习方法的语义分类。此外,我们以时间顺序排列,其进化进展和评估标准(数据集内集和数据集互联集合中集)覆盖了FAS的主要公共数据集。最后,我们讨论了开放的研究挑战和未来方向。
translated by 谷歌翻译
基于无监督的域适应性(UDA),由于目标情景的表现有希望的表现,面部抗散热器(FAS)方法引起了人们的注意。大多数现有的UDA FAS方法通常通过对齐语义高级功能的分布来拟合受过训练的模型。但是,对未标记的目标域的监督不足,低水平特征对齐降低了现有方法的性能。为了解决这些问题,我们提出了UDA FAS的新颖观点,该视角将目标数据直接适合于模型,即,通过图像翻译将目标数据风格化为源域样式,并进一步将风格化的数据提供给训练有素的数据分类的源模型。提出的生成域适应(GDA)框架结合了两个精心设计的一致性约束:1)域间神经统计量的一致性指导发生器缩小域间间隙。 2)双层语义一致性确保了风格化图像的语义质量。此外,我们提出了域内频谱混合物,以进一步扩大目标数据分布,以确保概括并减少域内间隙。广泛的实验和可视化证明了我们方法对最新方法的有效性。
translated by 谷歌翻译
随着各种面部表现攻击不断出现,基于域概括(DG)的面部抗散热(FAS)方法引起了人们的注意。现有的基于DG的FAS方法始终捕获用于概括各种看不见域的域不变功能。但是,他们忽略了单个源域的歧视性特征和不同域的不同域特异性信息,并且训练有素的模型不足以适应各种看不见的域。为了解决这个问题,我们提出了专家学习(AMEL)框架的自适应混合物,该框架利用了特定于域的信息以适应性地在可见的源域和看不见的目标域之间建立链接,以进一步改善概括。具体而言,特定领域的专家(DSE)旨在研究歧视性和独特的域特异性特征,以作为对共同域不变特征的补充。此外,提出了动态专家聚合(DEA),以根据与看不见的目标域相关的域相关的每个源专家的互补信息来自适应地汇总信息。并结合元学习,这些模块合作,可适应各种看不见的目标域的有意义的特定于域特异性信息。广泛的实验和可视化证明了我们对最先进竞争者的方法的有效性。
translated by 谷歌翻译
最近,无监督的人重新识别(RE-ID)引起了人们的关注,因为其开放世界情景设置有限,可用的带注释的数据有限。现有的监督方法通常无法很好地概括在看不见的域上,而无监督的方法(大多数缺乏多范围的信息),并且容易患有确认偏见。在本文中,我们旨在从两个方面从看不见的目标域上找到更好的特征表示形式,1)在标记的源域上进行无监督的域适应性和2)2)在未标记的目标域上挖掘潜在的相似性。此外,提出了一种协作伪标记策略,以减轻确认偏见的影响。首先,使用生成对抗网络将图像从源域转移到目标域。此外,引入了人身份和身份映射损失,以提高生成图像的质量。其次,我们提出了一个新颖的协作多元特征聚类框架(CMFC),以学习目标域的内部数据结构,包括全局特征和部分特征分支。全球特征分支(GB)在人体图像的全球特征上采用了无监督的聚类,而部分特征分支(PB)矿山在不同人体区域内的相似性。最后,在两个基准数据集上进行的广泛实验表明,在无监督的人重新设置下,我们的方法的竞争性能。
translated by 谷歌翻译
Deep domain adaptation has emerged as a new learning technique to address the lack of massive amounts of labeled data. Compared to conventional methods, which learn shared feature subspaces or reuse important source instances with shallow representations, deep domain adaptation methods leverage deep networks to learn more transferable representations by embedding domain adaptation in the pipeline of deep learning. There have been comprehensive surveys for shallow domain adaptation, but few timely reviews the emerging deep learning based methods. In this paper, we provide a comprehensive survey of deep domain adaptation methods for computer vision applications with four major contributions. First, we present a taxonomy of different deep domain adaptation scenarios according to the properties of data that define how two domains are diverged. Second, we summarize deep domain adaptation approaches into several categories based on training loss, and analyze and compare briefly the state-of-the-art methods under these categories. Third, we overview the computer vision applications that go beyond image classification, such as face recognition, semantic segmentation and object detection. Fourth, some potential deficiencies of current methods and several future directions are highlighted.
translated by 谷歌翻译
虽然无监督的域适应(UDA)算法,即,近年来只有来自源域的标记数据,大多数算法和理论结果侧重于单源无监督域适应(SUDA)。然而,在实际情况下,标记的数据通常可以从多个不同的源收集,并且它们可能不仅不同于目标域而且彼此不同。因此,来自多个源的域适配器不应以相同的方式进行建模。最近基于深度学习的多源无监督域适应(Muda)算法专注于通过在通用特征空间中的所有源极和目标域的分布对齐来提取所有域的公共域不变表示。但是,往往很难提取Muda中所有域的相同域不变表示。此外,这些方法匹配分布而不考虑类之间的域特定的决策边界。为了解决这些问题,我们提出了一个新的框架,具有两个对准阶段的Muda,它不仅将每对源和目标域的分布对齐,而且还通过利用域特定的分类器的输出对准决策边界。广泛的实验表明,我们的方法可以对图像分类的流行基准数据集实现显着的结果。
translated by 谷歌翻译
面部表现攻击检测(PAD)的域适应性(DA)或域概括(DG)最近以其对看不见的攻击情景的鲁棒性引起了人们的注意。但是,现有的基于DA/DG的PAD方法尚未完全探索可以提供有关攻击样式知识(例如材料,背景,照明和分辨率)的知识的特定领域样式信息。在本文中,我们引入了一种新型样式引导的域适应性(SGDA)框架,用于推理时间自适应垫。具体而言,提出了样式选择性归一化(SSN),以探索高阶功能统计信息中特定领域的样式信息。提出的SSN通过减少目标域和源域之间的样式差异,使模型适应目标域。此外,我们仔细设计了风格的元学习(SAML)来增强适应能力,该能力模拟了虚拟测试域上的样式选择过程的推理时间适应。与以前的域适应方法相反,我们的方法不需要其他辅助模型(例如,域适配器)或训练过程中未标记的目标域,这使我们的方法更加实用。为了验证我们的实验,我们使用公共数据集:MSU-MFSD,CASIA-FASD,OULU-NPU和IDIAP REPLAYATTACK。在大多数评估中,与常规的基于DA/DG的PAD方法相比,结果表明性能差距显着。
translated by 谷歌翻译
凝视和头部姿势估计模型的鲁棒性高度取决于标记的数据量。最近,生成建模在生成照片现实图像方面表现出了出色的结果,这可以减轻对标记数据的需求。但是,在新领域采用这种生成模型,同时保持其对不同图像属性的细粒度控制的能力,例如,凝视和头部姿势方向,是一个挑战性的问题。本文提出了Cuda-GHR,这是一种无监督的域适应框架,可以对凝视和头部姿势方向进行细粒度的控制,同时保留该人的外观相关因素。我们的框架同时学会了通过利用富含标签的源域和未标记的目标域来适应新的域和删除图像属性,例如外观,凝视方向和头部方向。基准测试数据集的广泛实验表明,所提出的方法在定量和定性评估上都可以胜过最先进的技术。此外,我们表明目标域中生成的图像标签对有效地传递知识并提高下游任务的性能。
translated by 谷歌翻译
Recent works on domain adaptation reveal the effectiveness of adversarial learning on filling the discrepancy between source and target domains. However, two common limitations exist in current adversarial-learning-based methods. First, samples from two domains alone are not sufficient to ensure domain-invariance at most part of latent space. Second, the domain discriminator involved in these methods can only judge real or fake with the guidance of hard label, while it is more reasonable to use soft scores to evaluate the generated images or features, i.e., to fully utilize the inter-domain information. In this paper, we present adversarial domain adaptation with domain mixup (DM-ADA), which guarantees domain-invariance in a more continuous latent space and guides the domain discriminator in judging samples' difference relative to source and target domains. Domain mixup is jointly conducted on pixel and feature level to improve the robustness of models. Extensive experiments prove that the proposed approach can achieve superior performance on tasks with various degrees of domain shift and data complexity.
translated by 谷歌翻译
在本文中,我们提出了一种使用域鉴别特征模块的双模块网络架构,以鼓励域不变的特征模块学习更多域不变的功能。该建议的架构可以应用于任何利用域不变功能的任何模型,用于无监督域适应,以提高其提取域不变特征的能力。我们在作为代表性算法的神经网络(DANN)模型的区域 - 对抗训练进行实验。在培训过程中,我们为两个模块提供相同的输入,然后分别提取它们的特征分布和预测结果。我们提出了差异损失,以找到预测结果的差异和两个模块之间的特征分布。通过对抗训练来最大化其特征分布和最小化其预测结果的差异,鼓励两个模块分别学习更多域歧视和域不变特征。进行了广泛的比较评估,拟议的方法在大多数无监督的域适应任务中表现出最先进的。
translated by 谷歌翻译
由于其在保护面部识别系统免于演示攻击(PAS)中的至关重要的作用,因此面部抗散热器(FAS)最近引起了人们的关注。随着越来越现实的PA随着新颖类型的发展,由于其表示能力有限,基于手工特征的传统FAS方法变得不可靠。随着近十年来大规模学术数据集的出现,基于深度学习的FA实现了卓越的性能并占据了这一领域。但是,该领域的现有评论主要集中在手工制作的功能上,这些功能过时,对FAS社区的进步没有任何启发。在本文中,为了刺激未来的研究,我们对基于深度学习的FAS的最新进展进行了首次全面综述。它涵盖了几个新颖且有见地的组成部分:1)除了使用二进制标签的监督(例如,``0'''for pas vs.'1'),我们还通过像素智能监督(例如,伪深度图)调查了最新方法; 2)除了传统的数据内评估外,我们还收集和分析专门为域概括和开放式FAS设计的最新方法; 3)除了商用RGB摄像机外,我们还总结了多模式(例如,深度和红外线)或专门(例如,光场和闪存)传感器下的深度学习应用程序。我们通过强调当前的开放问题并突出潜在的前景来结束这项调查。
translated by 谷歌翻译
语义分割在广泛的计算机视觉应用中起着基本作用,提供了全球对图像​​的理解的关键信息。然而,最先进的模型依赖于大量的注释样本,其比在诸如图像分类的任务中获得更昂贵的昂贵的样本。由于未标记的数据替代地获得更便宜,因此无监督的域适应达到了语义分割社区的广泛成功并不令人惊讶。本调查致力于总结这一令人难以置信的快速增长的领域的五年,这包含了语义细分本身的重要性,以及将分段模型适应新环境的关键需求。我们提出了最重要的语义分割方法;我们对语义分割的域适应技术提供了全面的调查;我们揭示了多域学习,域泛化,测试时间适应或无源域适应等较新的趋势;我们通过描述在语义细分研究中最广泛使用的数据集和基准测试来结束本调查。我们希望本调查将在学术界和工业中提供具有全面参考指导的研究人员,并有助于他们培养现场的新研究方向。
translated by 谷歌翻译
With the increasing variations of face presentation attacks, model generalization becomes an essential challenge for a practical face anti-spoofing system. This paper presents a generalized face anti-spoofing framework that consists of three tasks: depth estimation, face parsing, and live/spoof classification. With the pixel-wise supervision from the face parsing and depth estimation tasks, the regularized features can better distinguish spoof faces. While simulating domain shift with meta-learning techniques, the proposed one-side triplet loss can further improve the generalization capability by a large margin. Extensive experiments on four public datasets demonstrate that the proposed framework and training strategies are more effective than previous works for model generalization to unseen domains.
translated by 谷歌翻译
睡眠分期在诊断和治疗睡眠障碍中非常重要。最近,已经提出了许多数据驱动的深度学习模型,用于自动睡眠分期。他们主要在一个大型公共标签的睡眠数据集上训练该模型,并在较小的主题上对其进行测试。但是,他们通常认为火车和测试数据是从相同的分布中绘制的,这可能在现实世界中不存在。最近已经开发了无监督的域适应性(UDA)来处理此域移位问题。但是,以前用于睡眠分期的UDA方法具有两个主要局限性。首先,他们依靠一个完全共享的模型来对齐,该模型可能会在功能提取过程中丢失特定于域的信息。其次,它们仅在全球范围内将源和目标分布对齐,而无需考虑目标域中的类信息,从而阻碍了测试时模型的分类性能。在这项工作中,我们提出了一个名为Adast的新型对抗性学习框架,以解决未标记的目标域中的域转移问题。首先,我们开发了一个未共享的注意机制,以保留两个领域中的域特异性特征。其次,我们设计了一种迭代自我训练策略,以通过目标域伪标签提高目标域上的分类性能。我们还建议双重分类器,以提高伪标签的鲁棒性和质量。在六个跨域场景上的实验结果验证了我们提出的框架的功效及其优于最先进的UDA方法。源代码可在https://github.com/emadeldeen24/adast上获得。
translated by 谷歌翻译
In this paper, we investigate a challenging unsupervised domain adaptation setting -unsupervised model adaptation. We aim to explore how to rely only on unlabeled target data to improve performance of an existing source prediction model on the target domain, since labeled source data may not be available in some real-world scenarios due to data privacy issues. For this purpose, we propose a new framework, which is referred to as collaborative class conditional generative adversarial net to bypass the dependence on the source data. Specifically, the prediction model is to be improved through generated target-style data, which provides more accurate guidance for the generator. As a result, the generator and the prediction model can collaborate with each other without source data. Furthermore, due to the lack of supervision from source data, we propose a weight constraint that encourages similarity to the source model. A clustering-based regularization is also introduced to produce more discriminative features in the target domain. Compared to conventional domain adaptation methods, our model achieves superior performance on multiple adaptation tasks with only unlabeled target data, which verifies its effectiveness in this challenging setting.
translated by 谷歌翻译
Domain adaptation is critical for success in new, unseen environments. Adversarial adaptation models applied in feature spaces discover domain invariant representations, but are difficult to visualize and sometimes fail to capture pixel-level and low-level domain shifts. Recent work has shown that generative adversarial networks combined with cycle-consistency constraints are surprisingly effective at mapping images between domains, even without the use of aligned image pairs. We propose a novel discriminatively-trained Cycle-Consistent Adversarial Domain Adaptation model. CyCADA adapts representations at both the pixel-level and feature-level, enforces cycle-consistency while leveraging a task loss, and does not require aligned pairs. Our model can be applied in a variety of visual recognition and prediction settings. We show new state-of-the-art results across multiple adaptation tasks, including digit classification and semantic segmentation of road scenes demonstrating transfer from synthetic to real world domains.
translated by 谷歌翻译
Adversarial learning methods are a promising approach to training robust deep networks, and can generate complex samples across diverse domains. They also can improve recognition despite the presence of domain shift or dataset bias: several adversarial approaches to unsupervised domain adaptation have recently been introduced, which reduce the difference between the training and test domain distributions and thus improve generalization performance. Prior generative approaches show compelling visualizations, but are not optimal on discriminative tasks and can be limited to smaller shifts. Prior discriminative approaches could handle larger domain shifts, but imposed tied weights on the model and did not exploit a GAN-based loss. We first outline a novel generalized framework for adversarial adaptation, which subsumes recent state-of-the-art approaches as special cases, and we use this generalized view to better relate the prior approaches. We propose a previously unexplored instance of our general framework which combines discriminative modeling, untied weight sharing, and a GAN loss, which we call Adversarial Discriminative Domain Adaptation (ADDA). We show that ADDA is more effective yet considerably simpler than competing domain-adversarial methods, and demonstrate the promise of our approach by exceeding state-of-the-art unsupervised adaptation results on standard cross-domain digit classification tasks and a new more difficult cross-modality object classification task.
translated by 谷歌翻译