测试时间适应（TTA）是指适应神经网络以进行分配变化，仅在测试时间内从新域中访问未标记的测试样本。先前的TTA方法优化了无监督的目标，例如帐篷中的模型预测的熵[Wang等，2021]，但目前尚不清楚到底是什么使TTA损失良好。在本文中，我们首先提出一个令人惊讶的现象：如果我们尝试在广泛的功能上衡量最佳的TTA损失，那么我们恢复了与（温度缩放版本的）非常相似的函数帐篷采用的软磁性 - 凝集。但是，只有在我们正在适应的分类器通过跨凝结训练的情况下，这才能保持；如果通过平方损失训练，则会出现不同的最佳TTA损失。为了解释这一现象，我们通过训练损失的凸结合物分析了TTA。我们表明，在自然条件下，这种（无监督的）共轭功能可以看作是对原始监督损失的局部近似值，实际上，它恢复了元学习发现的最佳损失。这导致了一种通用食谱，可用于为通用类的任何给定监督培训损失功能找到良好的TTA损失。从经验上讲，我们的方法始终在广泛的基准测试中统治其他基线。当应用于新型损失功能的分类器时，我们的方法尤其令人感兴趣，例如，最近所传播的polyloss与基于熵的损失有很大的不同。此外，我们表明我们的方法也可以用非常特定的软标签解释为一种自我训练，我们将其称为共轭伪标记。总体而言，我们的方法为更好地理解和改善测试时间适应提供了广泛的框架。代码可在https://github.com/locuslab/tta_conjugate上找到。

We demonstrate that self-learning techniques like entropy minimization and pseudo-labeling are simple and effective at improving performance of a deployed computer vision model under systematic domain shifts. We conduct a wide range of large-scale experiments and show consistent improvements irrespective of the model architecture, the pre-training technique or the type of distribution shift. At the same time, self-learning is simple to use in practice because it does not require knowledge or access to the original training data or scheme, is robust to hyperparameter choices, is straight-forward to implement and requires only a few adaptation epochs. This makes self-learning techniques highly attractive for any practitioner who applies machine learning algorithms in the real world. We present state-of-the-art adaptation results on CIFAR10-C (8.5% error), ImageNet-C (22.0% mCE), ImageNet-R (17.4% error) and ImageNet-A (14.8% error), theoretically study the dynamics of self-supervised adaptation methods and propose a new classification dataset (ImageNet-D) which is challenging even with adaptation.

大多数机器学习算法的基本假设是培训和测试数据是从相同的底层分布中汲取的。然而，在几乎所有实际应用中违反了这种假设：由于不断变化的时间相关，非典型最终用户或其他因素，机器学习系统经常测试。在这项工作中，我们考虑域泛化的问题设置，其中训练数据被构造成域，并且可能有多个测试时间偏移，对应于新域或域分布。大多数事先方法旨在学习在所有域上执行良好的单一强大模型或不变的功能空间。相比之下，我们的目标是使用未标记的测试点学习适应域转移到域移的模型。我们的主要贡献是介绍自适应风险最小化（ARM）的框架，其中模型被直接优化，以便通过学习来转移以适应培训域来改编。与稳健性，不变性和适应性的先前方法相比，ARM方法提供了在表现域移位的多个图像分类问题上的性能增益为1-4％的测试精度。

Selective classification involves identifying the subset of test samples that a model can classify with high accuracy, and is important for applications such as automated medical diagnosis. We argue that this capability of identifying uncertain samples is valuable for training classifiers as well, with the aim of building more accurate classifiers. We unify these dual roles by training a single auxiliary meta-network to output an importance weight as a function of the instance. This measure is used at train time to reweight training data, and at test-time to rank test instances for selective classification. A second, key component of our proposal is the meta-objective of minimizing dropout variance (the variance of classifier output when subjected to random weight dropout) for training the metanetwork. We train the classifier together with its metanetwork using a nested objective of minimizing classifier loss on training data and meta-loss on a separate meta-training dataset. We outperform current state-of-the-art on selective classification by substantial margins--for instance, upto 1.9% AUC and 2% accuracy on a real-world diabetic retinopathy dataset. Finally, our meta-learning framework extends naturally to unsupervised domain adaptation, given our unsupervised variance minimization meta-objective. We show cumulative absolute gains of 3.4% / 3.3% accuracy and AUC over the other baselines in domain shift settings on the Retinopathy dataset using unsupervised domain adaptation.

Models should be able to adapt to unseen data during test-time to avoid performance drops caused by inevitable distribution shifts in real-world deployment scenarios. In this work, we tackle the practical yet challenging test-time adaptation (TTA) problem, where a model adapts to the target domain without accessing the source data. We propose a simple recipe called \textit{Data-efficient Prompt Tuning} (DePT) with two key ingredients. First, DePT plugs visual prompts into the vision Transformer and only tunes these source-initialized prompts during adaptation. We find such parameter-efficient finetuning can efficiently adapt the model representation to the target domain without overfitting to the noise in the learning objective. Second, DePT bootstraps the source representation to the target domain by memory bank-based online pseudo-labeling. A hierarchical self-supervised regularization specially designed for prompts is jointly optimized to alleviate error accumulation during self-training. With much fewer tunable parameters, DePT demonstrates not only state-of-the-art performance on major adaptation benchmarks VisDA-C, ImageNet-C, and DomainNet-126, but also superior data efficiency, i.e., adaptation with only 1\% or 10\% data without much performance degradation compared to 100\% data. In addition, DePT is also versatile to be extended to online or multi-source TTA settings.

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}。

本文提出了一种新颖的测试时间适应策略，该策略仅使用来自目标域的未标记的在线数据来调整在源域上预先训练的模型，以减轻由于源和目标域之间的分布变化而导致的性能降低。使用未标记的在线数据调整整个模型参数可能是有害的，这是由于无监督目标的错误信号。为了减轻此问题，我们提出了一个偏僻的权重正则化，该调整重量正规化鼓励在很大程度上更新模型参数对分布移位敏感的参数，同时在测试时间适应期间稍微更新那些对变化的不敏感的参数。这种正则化使该模型能够通过利用高学习率的好处来快速适应目标域而无需性能降低。此外，我们提出了一个基于最近的源原型来对齐源和目标特征的辅助任务，这有​​助于减少分布转移并导致进一步的性能提高。我们表明，我们的方法在各种标准基准方面展示了最先进的性能，甚至超过其监督的对手。

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。

我们理论上和经验地证明，对抗性鲁棒性可以显着受益于半体验学习。从理论上讲，我们重新审视了Schmidt等人的简单高斯模型。这显示了标准和稳健分类之间的示例复杂性差距。我们证明了未标记的数据桥接这种差距：简单的半体验学习程序（自我训练）使用相同数量的达到高标准精度所需的标签实现高的强大精度。经验上，我们增强了CiFar-10，使用50万微小的图像，使用了8000万微小的图像，并使用强大的自我训练来优于最先进的鲁棒精度（i）$ \ ell_ infty $鲁棒性通过对抗培训和（ii）认证$ \ ell_2 $和$ \ ell_ \ infty $鲁棒性通过随机平滑的几个强大的攻击。在SVHN上，添加DataSet自己的额外训练集，删除的标签提供了4到10个点的增益，在使用额外标签的1点之内。

我们考虑了源模型的无监督域适应的新问题，而无需访问语义分段的源数据。无监督的域适配旨在使标记为源数据的模型调整到新的未标记目标数据集。现有方法假设源数据在自适应期间与目标数据一起使用。但是，在实际情况下，由于在本工作中的原因，我们只能访问源模型和未标记的目标数据，但不是标记的来源，我们提出了一种自我训练方法从源模型中提取知识。要弥补从源到目标的分发班次，我们首先使用未标记的目标数据更新网络的标准化参数。然后我们采用信心过滤的伪标签，并强制执行某些转换。尽管非常简单直观，但我们的框架能够在我们广泛的实验和消融研究中直接应用于目标数据的源模型来实现显着的性能。事实上，性能只是几个远离最近的最先进的方法，它使用源数据进行适应。我们进一步展示了完全测试时间适应设置的所提出方法的恒定性，在那里我们不需要任何目标培训数据并仅在测试时适应。

Recent reports suggest that a generic supervised deep CNN model trained on a large-scale dataset reduces, but does not remove, dataset bias. Fine-tuning deep models in a new domain can require a significant amount of labeled data, which for many applications is simply not available. We propose a new CNN architecture to exploit unlabeled and sparsely labeled target domain data. Our approach simultaneously optimizes for domain invariance to facilitate domain transfer and uses a soft label distribution matching loss to transfer information between tasks. Our proposed adaptation method offers empirical performance which exceeds previously published results on two standard benchmark visual domain adaptation tasks, evaluated across supervised and semi-supervised adaptation settings.

Test-time adaptation is the problem of adapting a source pre-trained model using test inputs from a target domain without access to source domain data. Most of the existing approaches address the setting in which the target domain is stationary. Moreover, these approaches are prone to making erroneous predictions with unreliable uncertainty estimates when distribution shifts occur. Hence, test-time adaptation in the face of non-stationary target domain shift becomes a problem of significant interest. To address these issues, we propose a principled approach, PETAL (Probabilistic lifElong Test-time Adaptation with seLf-training prior), which looks into this problem from a probabilistic perspective using a partly data-dependent prior. A student-teacher framework, where the teacher model is an exponential moving average of the student model naturally emerges from this probabilistic perspective. In addition, the knowledge from the posterior distribution obtained for the source task acts as a regularizer. To handle catastrophic forgetting in the long term, we also propose a data-driven model parameter resetting mechanism based on the Fisher information matrix (FIM). Moreover, improvements in experimental results suggest that FIM based data-driven parameter restoration contributes to reducing the error accumulation and maintaining the knowledge of recent domain by restoring only the irrelevant parameters. In terms of predictive error rate as well as uncertainty based metrics such as Brier score and negative log-likelihood, our method achieves better results than the current state-of-the-art for online lifelong test time adaptation across various benchmarks, such as CIFAR-10C, CIFAR-100C, ImageNetC, and ImageNet3DCC datasets.

Semi-supervised learning (SSL) provides an effective means of leveraging unlabeled data to improve a model's performance. This domain has seen fast progress recently, at the cost of requiring more complex methods. In this paper we propose FixMatch, an algorithm that is a significant simplification of existing SSL methods. FixMatch first generates pseudo-labels using the model's predictions on weaklyaugmented unlabeled images. For a given image, the pseudo-label is only retained if the model produces a high-confidence prediction. The model is then trained to predict the pseudo-label when fed a strongly-augmented version of the same image. Despite its simplicity, we show that FixMatch achieves state-of-the-art performance across a variety of standard semi-supervised learning benchmarks, including 94.93% accuracy on CIFAR-10 with 250 labels and 88.61% accuracy with 40 -just 4 labels per class. We carry out an extensive ablation study to tease apart the experimental factors that are most important to FixMatch's success. The code is available at https://github.com/google-research/fixmatch.

Source-free domain adaptation (SFDA) aims to transfer knowledge learned from a source domain to an unlabeled target domain, where the source data is unavailable during adaptation. Existing approaches for SFDA focus on self-training usually including well-established entropy minimization techniques. One of the main challenges in SFDA is to reduce accumulation of errors caused by domain misalignment. A recent strategy successfully managed to reduce error accumulation by pseudo-labeling the target samples based on class-wise prototypes (centroids) generated by their clustering in the representation space. However, this strategy also creates cases for which the cross-entropy of a pseudo-label and the minimum entropy have a conflict in their objectives. We call this conflict the centroid-hypothesis conflict. We propose to reconcile this conflict by aligning the entropy minimization objective with that of the pseudo labels' cross entropy. We demonstrate the effectiveness of aligning the two loss objectives on three domain adaptation datasets. In addition, we provide state-of-the-art results using up-to-date architectures also showing the consistency of our method across these architectures.

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.

半监督学习（SSL）是规避建立高性能模型的昂贵标签成本的最有前途的范例之一。大多数现有的SSL方法常规假定标记和未标记的数据是从相同（类）分布中绘制的。但是，在实践中，未标记的数据可能包括课外样本；那些不能从标签数据中的封闭类中的单热编码标签，即未标记的数据是开放设置。在本文中，我们介绍了Opencos，这是一种基于最新的自我监督视觉表示学习框架来处理这种现实的半监督学习方案。具体而言，我们首先观察到，可以通过自我监督的对比度学习有效地识别开放式未标记数据集中的类外样本。然后，Opencos利用此信息来克服现有的最新半监督方法中的故障模式，通过利用一式旋转伪标签和软标签来为已识别的识别和外部未标记的标签数据分别。我们广泛的实验结果表明了Opencos的有效性，可以修复最新的半监督方法，适合涉及开放式无标记数据的各种情况。

Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled data when labels are limited or expensive to obtain. SSL algorithms based on deep neural networks have recently proven successful on standard benchmark tasks. However, we argue that these benchmarks fail to address many issues that SSL algorithms would face in real-world applications. After creating a unified reimplementation of various widely-used SSL techniques, we test them in a suite of experiments designed to address these issues. We find that the performance of simple baselines which do not use unlabeled data is often underreported, SSL methods differ in sensitivity to the amount of labeled and unlabeled data, and performance can degrade substantially when the unlabeled dataset contains out-ofdistribution examples. To help guide SSL research towards real-world applicability, we make our unified reimplemention and evaluation platform publicly available. 2 * Equal contribution 2 https://github.com/brain-research/realistic-ssl-evaluation 32nd Conference on Neural Information Processing Systems (NeurIPS 2018),

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。

This work tackles the problem of semi-supervised learning of image classifiers. Our main insight is that the field of semi-supervised learning can benefit from the quickly advancing field of self-supervised visual representation learning. Unifying these two approaches, we propose the framework of self-supervised semi-supervised learning (S 4 L) and use it to derive two novel semi-supervised image classification methods. We demonstrate the effectiveness of these methods in comparison to both carefully tuned baselines, and existing semi-supervised learning methods. We then show that S 4 L and existing semi-supervised methods can be jointly trained, yielding a new state-of-the-art result on semi-supervised ILSVRC-2012 with 10% of labels.

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。