无监督域适应(UDA)旨在将知识从标记的源域传输到未标记的目标域。传统上,基于子空间的方法为此问题形成了一类重要的解决方案。尽管他们的数学优雅和易腐烂性,但这些方法通常被发现在产生具有复杂的现实世界数据集的领域不变的功能时无效。由于近期具有深度网络的代表学习的最新进展,本文重新访问了UDA的子空间对齐,提出了一种新的适应算法,始终如一地导致改进的泛化。与现有的基于对抗培训的DA方法相比,我们的方法隔离了特征学习和分配对准步骤,并利用主要辅助优化策略来有效地平衡域不契约的目标和模型保真度。在提供目标数据和计算要求的显着降低的同时,基于子空间的DA竞争性,有时甚至优于几种标准UDA基准测试的最先进的方法。此外,子空间对准导致本质上定期的模型,即使在具有挑战性的部分DA设置中,也表现出强大的泛化。最后,我们的UDA框架的设计本身支持对测试时间的新目标域的逐步适应,而无需从头开始重新检测模型。总之,由强大的特征学习者和有效的优化策略提供支持,我们将基于子空间的DA建立为可视识别的高效方法。
translated by 谷歌翻译
部署的ML模型的基本要求是从与培训不同的测试分布中汲取的数据概括。解决此问题的一个流行解决方案是,仅使用未标记的数据将预训练的模型调整为新的域。在本文中,我们关注该问题的挑战性变体,其中访问原始源数据受到限制。虽然完全测试时间适应(FTTA)和无监督的域适应性(UDA)密切相关,但由于大多数UDA方法需要访问源数据,因此UDA的进展不容易适用于TTA。因此,我们提出了一种新方法,即Cattan,它通过放松了通过新颖的深层子空间对准策略来放松访问整个源数据的需求,从而弥合了UDA和FTTA。通过为源数据存储的子空间基础设置的最小开销,Cattan在适应过程中可以在源数据和目标数据之间进行无监督的对齐。通过对多个2D和3D Vision基准测试(Imagenet-C,Office-31,OfficeHome,Domainnet,PointDa-10)和模型体系结构进行广泛的实验评估,我们在FTTA性能方面表现出显着提高。此外,即使使用固有健壮的模型,预训练的VIT表示以及目标域中的样本可用性低,我们也会对对齐目标的实用性做出许多关键发现。
translated by 谷歌翻译
无监督域适应(UDA)旨在将知识从相关但不同的良好标记的源域转移到新的未标记的目标域。大多数现有的UDA方法需要访问源数据,因此当数据保密而不相配在隐私问题时,不适用。本文旨在仅使用培训的分类模型来解决现实设置,而不是访问源数据。为了有效地利用适应源模型,我们提出了一种新颖的方法,称为源假设转移(拍摄),其通过将目标数据特征拟合到冻结源分类模块(表示分类假设)来学习目标域的特征提取模块。具体而言,拍摄挖掘出于特征提取模块的信息最大化和自我监督学习,以确保目标特征通过同一假设与看不见的源数据的特征隐式对齐。此外,我们提出了一种新的标签转移策略,它基于预测的置信度(标签信息),然后采用半监督学习来将目标数据分成两个分裂,然后提高目标域中的较为自信预测的准确性。如果通过拍摄获得预测,我们表示标记转移为拍摄++。关于两位数分类和对象识别任务的广泛实验表明,拍摄和射击++实现了与最先进的结果超越或相当的结果,展示了我们对各种视域适应问题的方法的有效性。代码可用于\ url {https://github.com/tim-learn/shot-plus}。
translated by 谷歌翻译
虽然在许多域内生成并提供了大量的未标记数据,但对视觉数据的自动理解的需求高于以往任何时候。大多数现有机器学习模型通常依赖于大量标记的训练数据来实现高性能。不幸的是,在现实世界的应用中,不能满足这种要求。标签的数量有限,手动注释数据昂贵且耗时。通常需要将知识从现有标记域传输到新域。但是,模型性能因域之间的差异(域移位或数据集偏差)而劣化。为了克服注释的负担,域适应(DA)旨在在将知识从一个域转移到另一个类似但不同的域中时减轻域移位问题。无监督的DA(UDA)处理标记的源域和未标记的目标域。 UDA的主要目标是减少标记的源数据和未标记的目标数据之间的域差异,并在培训期间在两个域中学习域不变的表示。在本文中,我们首先定义UDA问题。其次,我们从传统方法和基于深度学习的方法中概述了不同类别的UDA的最先进的方法。最后,我们收集常用的基准数据集和UDA最先进方法的报告结果对视觉识别问题。
translated by 谷歌翻译
Top-performing deep architectures are trained on massive amounts of labeled data. In the absence of labeled data for a certain task, domain adaptation often provides an attractive option given that labeled data of similar nature but from a different domain (e.g. synthetic images) are available. Here, we propose a new approach to domain adaptation in deep architectures that can be trained on large amount of labeled data from the source domain and large amount of unlabeled data from the target domain (no labeled targetdomain data is necessary).As the training progresses, the approach promotes the emergence of "deep" features that are (i) discriminative for the main learning task on the source domain and (ii) invariant with respect to the shift between the domains. We show that this adaptation behaviour can be achieved in almost any feed-forward model by augmenting it with few standard layers and a simple new gradient reversal layer. The resulting augmented architecture can be trained using standard backpropagation.Overall, the approach can be implemented with little effort using any of the deep-learning packages. The method performs very well in a series of image classification experiments, achieving adaptation effect in the presence of big domain shifts and outperforming previous state-ofthe-art on Office datasets.
translated by 谷歌翻译
深度学习(DL)是各种计算机视觉任务中使用的主要方法,因为它在许多任务上取得了相关结果。但是,在具有部分或没有标记数据的实际情况下,DL方法也容易出现众所周知的域移位问题。多源无监督的域适应性(MSDA)旨在通过从一袋源模型中分配弱知识来学习未标记域的预测指标。但是,大多数作品进行域适应性仅利用提取的特征并从损失函数设计的角度降低其域的转移。在本文中,我们认为仅基于域级特征处理域移动不足,但是在功能空间上对此类信息进行对齐也是必不可少的。与以前的工作不同,我们专注于网络设计,并建议将多源版本的域对齐层(MS-DIAL)嵌入预测变量的不同级别。这些层旨在匹配不同域之间的特征分布,并且可以轻松地应用于各种MSDA方法。为了显示我们方法的鲁棒性,我们考虑了两个具有挑战性的情况:数字识别和对象分类,进行了广泛的实验评估。实验结果表明,我们的方法可以改善最新的MSDA方法,从而在其分类精度上获得 +30.64%的相对增长。
translated by 谷歌翻译
Adversarial learning has been embedded into deep networks to learn disentangled and transferable representations for domain adaptation. Existing adversarial domain adaptation methods may not effectively align different domains of multimodal distributions native in classification problems. In this paper, we present conditional adversarial domain adaptation, a principled framework that conditions the adversarial adaptation models on discriminative information conveyed in the classifier predictions. Conditional domain adversarial networks (CDANs) are designed with two novel conditioning strategies: multilinear conditioning that captures the crosscovariance between feature representations and classifier predictions to improve the discriminability, and entropy conditioning that controls the uncertainty of classifier predictions to guarantee the transferability. With theoretical guarantees and a few lines of codes, the approach has exceeded state-of-the-art results on five datasets.
translated by 谷歌翻译
Domain adaptation enables the learner to safely generalize into novel environments by mitigating domain shifts across distributions. Previous works may not effectively uncover the underlying reasons that would lead to the drastic model degradation on the target task. In this paper, we empirically reveal that the erratic discrimination of the target domain mainly stems from its much smaller feature norms with respect to that of the source domain. To this end, we propose a novel parameter-free Adaptive Feature Norm approach. We demonstrate that progressively adapting the feature norms of the two domains to a large range of values can result in significant transfer gains, implying that those task-specific features with larger norms are more transferable. Our method successfully unifies the computation of both standard and partial domain adaptation with more robustness against the negative transfer issue. Without bells and whistles but a few lines of code, our method substantially lifts the performance on the target task and exceeds state-of-the-arts by a large margin (11.5% on Office-Home [45] and 17.1% on VisDA2017 [31]). We hope our simple yet effective approach will shed some light on the future research of transfer learning. Code is available at https://github.com/jihanyang/AFN .
translated by 谷歌翻译
域适应(DA)旨在将知识从标签富裕但异构的域转移到标签恐慌域,这减轻了标签努力并吸引了相当大的关注。与以前的方法不同,重点是学习域中的特征表示,一些最近的方法存在通用半监督学习(SSL)技术,直接将它们应用于DA任务,甚至实现竞争性能。最受欢迎的SSL技术之一是伪标记,可通过标记数据训练的分类器为每个未标记数据分配伪标签。但是,它忽略了DA问题的分布偏移,并且不可避免地偏置为源数据。要解决此问题,我们提出了一个名为辅助目标域导向的分类器(ATDOC)的新伪标签框架。 ATDOC通过为目标数据引入辅助分类器来缓解分类器偏置,以提高伪标签的质量。具体地,我们使用内存机制并开发两种类型的非参数分类器,即最近的质心分类器和邻域聚合,而不引入任何其他网络参数。尽管在伪分类目标中具有简单性,但具有邻域聚集的ATDOC显着优于域对齐技术和现有的SSL技术,以及甚至瘢痕标记的SSL任务。
translated by 谷歌翻译
关于无监督域适应性(UDA)的大多数现有研究都认为每个域的训练样本都带有域标签(例如绘画,照片)。假定每个域中的样品都遵循相同的分布,并利用域标签通过特征对齐来学习域不变特征。但是,这样的假设通常并不成立 - 通常存在许多较细粒的领域(例如,已经开发出了数十种现代绘画样式,每种绘画样式与经典风格的范围都有很大不同)。因此,在每个人工定义和粗粒结构域之间强迫特征分布对齐可能是无效的。在本文中,我们从完全不同的角度解决了单源和多源UDA,即将每个实例视为一个良好的域。因此,跨域的特征对齐是冗余。相反,我们建议执行动态实例域的适应性(DIDA)。具体而言,开发了具有自适应卷积内核的动态神经网络,以生成实例自适应残差,以使域 - 无知的深度特征适应每个单独的实例。这使得共享分类器可以同时应用于源域数据,而无需依赖任何域注释。此外,我们没有施加复杂的特征对准损失,而是仅使用标记的源和伪标记为目标数据的跨透镜损失采用简单的半监督学习范式。我们的模型被称为DIDA-NET,可以在几种常用的单源和多源UDA数据集上实现最先进的性能,包括数字,办公室房屋,域名,域名,Digit-Five和PAC。
translated by 谷歌翻译
半监督域适应(SSDA)是一种具有挑战性的问题,需要克服1)以朝向域的较差的数据和2)分布换档的方法。不幸的是,由于培训数据偏差朝标标样本训练,域适应(DA)和半监督学习(SSL)方法的简单组合通常无法解决这两个目的。在本文中,我们介绍了一种自适应结构学习方法,以规范SSL和DA的合作。灵感来自多视图学习,我们建议的框架由共享特征编码器网络和两个分类器网络组成,用于涉及矛盾的目的。其中,其中一个分类器被应用于组目标特征以提高级别的密度,扩大了鲁棒代表学习的分类集群的间隙。同时,其他分类器作为符号器,试图散射源功能以增强决策边界的平滑度。目标聚类和源扩展的迭代使目标特征成为相应源点的扩张边界内的封闭良好。对于跨域特征对齐和部分标记的数据学习的联合地址,我们应用最大平均差异(MMD)距离最小化和自培训(ST)将矛盾结构投影成共享视图以进行可靠的最终决定。对标准SSDA基准的实验结果包括Domainnet和Office-Home,展示了我们对最先进的方法的方法的准确性和稳健性。
translated by 谷歌翻译
无监督的域适应性(DA)中的主要挑战是减轻源域和目标域之间的域移动。先前的DA工作表明,可以使用借口任务来通过学习域不变表示来减轻此域的转移。但是,实际上,我们发现大多数现有的借口任务对其他已建立的技术无效。因此,我们从理论上分析了如何以及何时可以利用子公司借口任务来协助给定DA问题的目标任务并制定客观的子公司任务适用性标准。基于此标准,我们设计了一个新颖的贴纸干预过程和铸造贴纸分类的过程,作为监督的子公司DA问题,该问题与目标任务无监督的DA同时发生。我们的方法不仅改善了目标任务适应性能,而且还促进了面向隐私的无源DA,即没有并发源目标访问。标准Office-31,Office-Home,Domainnet和Visda基准的实验证明了我们对单源和多源无源DA的优势。我们的方法还补充了现有的无源作品,从而实现了领先的绩效。
translated by 谷歌翻译
Unsupervised domain adaptation (UDA) aims to leverage the knowledge learned from a labeled source dataset to solve similar tasks in a new unlabeled domain. Prior UDA methods typically require to access the source data when learning to adapt the model, making them risky and inefficient for decentralized private data. This work tackles a practical setting where only a trained source model is available and investigates how we can effectively utilize such a model without source data to solve UDA problems. We propose a simple yet generic representation learning framework, named Source HypOthesis Transfer (SHOT). SHOT freezes the classifier module (hypothesis) of the source model and learns the target-specific feature extraction module by exploiting both information maximization and selfsupervised pseudo-labeling to implicitly align representations from the target domains to the source hypothesis. To verify its versatility, we evaluate SHOT in a variety of adaptation cases including closed-set, partial-set, and open-set domain adaptation. Experiments indicate that SHOT yields state-of-the-art results among multiple domain adaptation benchmarks.
translated by 谷歌翻译
We introduce a new representation learning approach for domain adaptation, in which data at training and test time come from similar but different distributions. Our approach is directly inspired by the theory on domain adaptation suggesting that, for effective domain transfer to be achieved, predictions must be made based on features that cannot discriminate between the training (source) and test (target) domains.The approach implements this idea in the context of neural network architectures that are trained on labeled data from the source domain and unlabeled data from the target domain (no labeled target-domain data is necessary). As the training progresses, the approach promotes the emergence of features that are (i) discriminative for the main learning task on the source domain and (ii) indiscriminate with respect to the shift between the domains. We show that this adaptation behaviour can be achieved in almost any feed-forward model by augmenting it with few standard layers and a new gradient reversal layer. The resulting augmented architecture can be trained using standard backpropagation and stochastic gradient descent, and can thus be implemented with little effort using any of the deep learning packages.We demonstrate the success of our approach for two distinct classification problems (document sentiment analysis and image classification), where state-of-the-art domain adaptation performance on standard benchmarks is achieved. We also validate the approach for descriptor learning task in the context of person re-identification application.
translated by 谷歌翻译
当部署和培训之间存在分配变化时,深层神经网络的性能恶化严重。域的概括(DG)旨在通过仅依靠一组源域来安全地传输模型以看不见目标域。尽管已经提出了各种DG方法,但最近的一项名为Domainbed的研究表明,其中大多数没有超过简单的经验风险最小化(ERM)。为此,我们提出了一个通用框架,该框架与现有的DG算法是正交的,并且可以始终如一地提高其性能。与以前的DG作品不同的是,在静态源模型上有希望成为通用的DG,我们提出的ADAODM会在测试时间适应不同目标域的源模型。具体而言,我们在共享域形式的特征提取器上创建多个域特异性分类器。特征提取器和分类器以对抗性方式进行了训练,其中特征提取器将输入样品嵌入到域不变的空间中,并且多个分类器捕获了每个分类器与特定源域有关的独特决策边界。在测试过程中,可以通过利用源分类器之间的预测分歧来有效地衡量目标和源域之间的分布差异。通过微调源模型以最大程度地减少测试时间的分歧,目标域特征与不变特征空间很好地对齐。我们验证了两种流行的DG方法,即ERM和Coral,以及四个DG基准,即VLCS,PACS,OfficeHome和TerrainCognita。结果表明,ADAODM稳定地提高了对看不见的域的概括能力,并实现了最先进的性能。
translated by 谷歌翻译
Domain Adaptation is an actively researched problem in Computer Vision. In this work, we propose an approach that leverages unsupervised data to bring the source and target distributions closer in a learned joint feature space. We accomplish this by inducing a symbiotic relationship between the learned embedding and a generative adversarial network. This is in contrast to methods which use the adversarial framework for realistic data generation and retraining deep models with such data. We demonstrate the strength and generality of our approach by performing experiments on three different tasks with varying levels of difficulty: (1) Digit classification (MNIST, SVHN and USPS datasets) (2) Object recognition using OFFICE dataset and (3) Domain adaptation from synthetic to real data. Our method achieves state-of-the art performance in most experimental settings and by far the only GAN-based method that has been shown to work well across different datasets such as OFFICE and DIGITS.
translated by 谷歌翻译
在图像分类中,获得足够的标签通常昂贵且耗时。为了解决这个问题,域适应通常提供有吸引力的选择,给出了来自类似性质但不同域的大量标记数据。现有方法主要对准单个结构提取的表示的分布,并且表示可以仅包含部分信息,例如,仅包含部分饱和度,亮度和色调信息。在这一行中,我们提出了多代表性适应,这可以大大提高跨域图像分类的分类精度,并且特别旨在对准由名为Inception Adaption Adationation模块(IAM)提取的多个表示的分布。基于此,我们呈现多色自适应网络(MRAN)来通过多表示对准完成跨域图像分类任务,该任向性可以捕获来自不同方面的信息。此外,我们扩展了最大的平均差异(MMD)来计算适应损耗。我们的方法可以通过扩展具有IAM的大多数前进模型来轻松实现,并且网络可以通过反向传播有效地培训。在三个基准图像数据集上进行的实验证明了备的有效性。代码已在https://github.com/easezyc/deep-transfer -learning上获得。
translated by 谷歌翻译
大多数无监督的域适应性(UDA)方法假设在模型适应过程中可用标记的源图像可用。但是,由于机密性问题或移动设备上的内存约束,这种假设通常是不可行的。为了解决这些问题,我们提出了一种简单但有效的无源UDA方法,该方法仅使用预训练的源模型和未标记的目标图像。我们的方法通过合并数据增强并以两个一致性目标训练功能生成器来捕获局部不确定性。鼓励功能生成器从头部分类器的决策边界学习一致的视觉功能。受到自我监督学习的启发,我们的方法促进了预测空间和特征空间之间的空间间比对,同时在特征空间内结合了空间的一致性,以减少源域和目标域之间的域间隙。我们还考虑了认知不确定性,以提高模型适应性能。对流行的UDA基准测试的广泛实验表明,我们的方法的性能是可比甚至优于香草UDA方法,而无需使用源图像或网络修改。
translated by 谷歌翻译
Unsupervised domain adaptation (UDA) aims to transfer knowledge from a well-labeled source domain to a different but related unlabeled target domain with identical label space. Currently, the main workhorse for solving UDA is domain alignment, which has proven successful. However, it is often difficult to find an appropriate source domain with identical label space. A more practical scenario is so-called partial domain adaptation (PDA) in which the source label set or space subsumes the target one. Unfortunately, in PDA, due to the existence of the irrelevant categories in the source domain, it is quite hard to obtain a perfect alignment, thus resulting in mode collapse and negative transfer. Although several efforts have been made by down-weighting the irrelevant source categories, the strategies used tend to be burdensome and risky since exactly which irrelevant categories are unknown. These challenges motivate us to find a relatively simpler alternative to solve PDA. To achieve this, we first provide a thorough theoretical analysis, which illustrates that the target risk is bounded by both model smoothness and between-domain discrepancy. Considering the difficulty of perfect alignment in solving PDA, we turn to focus on the model smoothness while discard the riskier domain alignment to enhance the adaptability of the model. Specifically, we instantiate the model smoothness as a quite simple intra-domain structure preserving (IDSP). To our best knowledge, this is the first naive attempt to address the PDA without domain alignment. Finally, our empirical results on multiple benchmark datasets demonstrate that IDSP is not only superior to the PDA SOTAs by a significant margin on some benchmarks (e.g., +10% on Cl->Rw and +8% on Ar->Rw ), but also complementary to domain alignment in the standard UDA
translated by 谷歌翻译
当源(训练)数据和目标(测试)数据之间存在域移动时,深网很容易降级。最近的测试时间适应方法更新了通过流数据部署在新目标环境中的预训练源模型的批归归式层,以减轻这种性能降低。尽管此类方法可以在不首先收集大型目标域数据集的情况下进行调整,但它们的性能取决于流媒体条件,例如迷你批量的大小和类别分布,在实践中可能无法预测。在这项工作中,我们提出了一个框架,以适应几个域的适应性,以应对数据有效适应的实际挑战。具体而言,我们提出了在预训练的源模型中对特征归一化统计量的约束优化,该模型由目标域的小支持集监督。我们的方法易于实现,并改善每类用于分类任务的示例较小的源模型性能。对5个跨域分类和4个语义分割数据集进行了广泛的实验表明,我们的方法比测试时间适应更准确,更可靠,同时不受流媒体条件的约束。
translated by 谷歌翻译