The well-documented presence of texture bias in modern convolutional neural networks has led to a plethora of algorithms that promote an emphasis on shape cues, often to support generalization to new domains. Yet, common datasets, benchmarks and general model selection strategies are missing, and there is no agreed, rigorous evaluation protocol. In this paper, we investigate difficulties and limitations when training networks with reduced texture bias. In particular, we also show that proper evaluation and meaningful comparisons between methods are not trivial. We introduce BiasBed, a testbed for texture- and style-biased training, including multiple datasets and a range of existing algorithms. It comes with an extensive evaluation protocol that includes rigorous hypothesis testing to gauge the significance of the results, despite the considerable training instability of some style bias methods. Our extensive experiments, shed new light on the need for careful, statistically founded evaluation protocols for style bias (and beyond). E.g., we find that some algorithms proposed in the literature do not significantly mitigate the impact of style bias at all. With the release of BiasBed, we hope to foster a common understanding of consistent and meaningful comparisons, and consequently faster progress towards learning methods free of texture bias. Code is available at https://github.com/D1noFuzi/BiasBed

The goal of domain generalization algorithms is to predict well on distributions different from those seen during training. While a myriad of domain generalization algorithms exist, inconsistencies in experimental conditions-datasets, architectures, and model selection criteria-render fair and realistic comparisons difficult. In this paper, we are interested in understanding how useful domain generalization algorithms are in realistic settings. As a first step, we realize that model selection is non-trivial for domain generalization tasks. Contrary to prior work, we argue that domain generalization algorithms without a model selection strategy should be regarded as incomplete. Next, we implement DOMAINBED, a testbed for domain generalization including seven multi-domain datasets, nine baseline algorithms, and three model selection criteria. We conduct extensive experiments using DO-MAINBED and find that, when carefully implemented, empirical risk minimization shows state-of-the-art performance across all datasets. Looking forward, we hope that the release of DOMAINBED, along with contributions from fellow researchers, will streamline reproducible and rigorous research in domain generalization. * Alphabetical order, equal contribution.Preprint. Under review.

最近证明，接受SGD训练的神经网络优先依赖线性预测的特征，并且可以忽略复杂的，同样可预测的功能。这种简单性偏见可以解释他们缺乏分布（OOD）的鲁棒性。学习任务越复杂，统计工件（即选择偏见，虚假相关性）的可能性就越大比学习的机制更简单。我们证明可以减轻简单性偏差并改善了OOD的概括。我们使用对其输入梯度对齐的惩罚来训练一组类似的模型以不同的方式拟合数据。我们从理论和经验上展示了这会导致学习更复杂的预测模式的学习。 OOD的概括从根本上需要超出I.I.D.示例，例如多个培训环境，反事实示例或其他侧面信息。我们的方法表明，我们可以将此要求推迟到独立的模型选择阶段。我们获得了SOTA的结果，可以在视觉域偏置数据和概括方面进行视觉识别。该方法 - 第一个逃避简单性偏见的方法 - 突出了需要更好地理解和控制深度学习中的归纳偏见。

The ability to quickly and accurately identify covariate shift at test time is a critical and often overlooked component of safe machine learning systems deployed in high-risk domains. While methods exist for detecting when predictions should not be made on out-of-distribution test examples, identifying distributional level differences between training and test time can help determine when a model should be removed from the deployment setting and retrained. In this work, we define harmful covariate shift (HCS) as a change in distribution that may weaken the generalization of a predictive model. To detect HCS, we use the discordance between an ensemble of classifiers trained to agree on training data and disagree on test data. We derive a loss function for training this ensemble and show that the disagreement rate and entropy represent powerful discriminative statistics for HCS. Empirically, we demonstrate the ability of our method to detect harmful covariate shift with statistical certainty on a variety of high-dimensional datasets. Across numerous domains and modalities, we show state-of-the-art performance compared to existing methods, particularly when the number of observed test samples is small.

Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by learning increasingly complex representations of object shapes. Some recent studies suggest a more important role of image textures. We here put these conflicting hypotheses to a quantitative test by evaluating CNNs and human observers on images with a texture-shape cue conflict. We show that ImageNettrained CNNs are strongly biased towards recognising textures rather than shapes, which is in stark contrast to human behavioural evidence and reveals fundamentally different classification strategies. We then demonstrate that the same standard architecture (ResNet-50) that learns a texture-based representation on ImageNet is able to learn a shape-based representation instead when trained on 'Stylized-ImageNet', a stylized version of ImageNet. This provides a much better fit for human behavioural performance in our well-controlled psychophysical lab setting (nine experiments totalling 48,560 psychophysical trials across 97 observers) and comes with a number of unexpected emergent benefits such as improved object detection performance and previously unseen robustness towards a wide range of image distortions, highlighting advantages of a shape-based representation.

大多数机器学习算法由一个或多个超参数配置，必须仔细选择并且通常会影响性能。为避免耗时和不可递销的手动试验和错误过程来查找性能良好的超参数配置，可以采用各种自动超参数优化（HPO）方法，例如，基于监督机器学习的重新采样误差估计。本文介绍了HPO后，本文审查了重要的HPO方法，如网格或随机搜索，进化算法，贝叶斯优化，超带和赛车。它给出了关于进行HPO的重要选择的实用建议，包括HPO算法本身，性能评估，如何将HPO与ML管道，运行时改进和并行化结合起来。这项工作伴随着附录，其中包含关于R和Python的特定软件包的信息，以及用于特定学习算法的信息和推荐的超参数搜索空间。我们还提供笔记本电脑，这些笔记本展示了这项工作的概念作为补充文件。

域泛化（DG）方法旨在开发概括到测试分布与训练数据不同的设置的模型。在本文中，我们专注于多源零拍DG的挑战性问题，其中来自多个源域的标记训练数据可用，但无法从目标域中访问数据。虽然这个问题已成为研究的重要话题，但令人惊讶的是，将所有源数据汇集在一起​​和培训单个分类器的简单解决方案在标准基准中具有竞争力。更重要的是，即使在不同域中明确地优化不变性的复杂方法也不一定提供对ERM的非微不足道的增益。在本文中，我们首次研究了预先指定的域标签和泛化性能之间的重要链接。使用动机案例研究和分布稳健优化算法的新变种，我们首先演示了如何推断的自定义域组可以通过数据集的原始域标签来实现一致的改进。随后，我们介绍了一种用于多域泛化，Muldens的一般方法，它使用基于ERM的深度合并骨干，并通过元优化算法执行隐式域重标。使用对多个标准基准测试的经验研究，我们表明Muldens不需要定制增强策略或特定于数据集的培训过程，始终如一地优于ERM，通过显着的边距，即使在比较时也会产生最先进的泛化性能对于利用域标签的现有方法。

Image classification with small datasets has been an active research area in the recent past. However, as research in this scope is still in its infancy, two key ingredients are missing for ensuring reliable and truthful progress: a systematic and extensive overview of the state of the art, and a common benchmark to allow for objective comparisons between published methods. This article addresses both issues. First, we systematically organize and connect past studies to consolidate a community that is currently fragmented and scattered. Second, we propose a common benchmark that allows for an objective comparison of approaches. It consists of five datasets spanning various domains (e.g., natural images, medical imagery, satellite data) and data types (RGB, grayscale, multispectral). We use this benchmark to re-evaluate the standard cross-entropy baseline and ten existing methods published between 2017 and 2021 at renowned venues. Surprisingly, we find that thorough hyper-parameter tuning on held-out validation data results in a highly competitive baseline and highlights a stunted growth of performance over the years. Indeed, only a single specialized method dating back to 2019 clearly wins our benchmark and outperforms the baseline classifier.

我们介绍了几个新的数据集即想象的A / O和Imagenet-R以及合成环境和测试套件，我们称为CAOS。 Imagenet-A / O允许研究人员专注于想象成剩余的盲点。由于追踪稳健的表示，以特殊创建了ImageNet-R，因为表示不再简单地自然，而是包括艺术和其他演绎。 Caos Suite由Carla Simulator构建，允许包含异常物体，可以创建可重复的合成环境和用于测试稳健性的场景。所有数据集都是为测试鲁棒性和衡量鲁棒性的衡量进展而创建的。数据集已用于各种其他作品中，以衡量其具有鲁棒性的自身进步，并允许切向进展，这些进展不会完全关注自然准确性。鉴于这些数据集，我们创建了几种旨在推进鲁棒性研究的新方法。我们以最大Logit的形式和典型程度的形式构建简单的基线，并以深度的形式创建新的数据增强方法，从而提高上述基准。最大Logit考虑Logit值而不是SoftMax操作后的值，而微小的变化会产生明显的改进。典型程分将输出分布与类的后部分布进行比较。我们表明，除了分段任务之外，这将提高对基线的性能。猜测可能在像素级别，像素的语义信息比类级信息的语义信息不太有意义。最后，新的Deepaulment的新增强技术利用神经网络在彻底不同于先前使用的传统几何和相机的转换的图像上创建增强。

对分布（OOD）数据的概括是人类自然的能力，但对于机器而言挑战。这是因为大多数学习算法强烈依赖于i.i.d.〜对源/目标数据的假设，这在域转移导致的实践中通常会违反。域的概括（DG）旨在通过仅使用源数据进行模型学习来实现OOD的概括。在过去的十年中，DG的研究取得了长足的进步，导致了广泛的方法论，例如，基于域的一致性，元学习，数据增强或合奏学习的方法，仅举几例；还在各个应用领域进行了研究，包括计算机视觉，语音识别，自然语言处理，医学成像和强化学习。在本文中，首次提供了DG中的全面文献综述，以总结过去十年来的发展。具体而言，我们首先通过正式定义DG并将其与其他相关领域（如域适应和转移学习）联系起来来涵盖背景。然后，我们对现有方法和理论进行了彻底的审查。最后，我们通过有关未来研究方向的见解和讨论来总结这项调查。

尽管进行了多年的研究，但跨域的概括仍然是深层网络的语义分割的关键弱点。先前的研究取决于静态模型的假设，即训练过程完成后，模型参数在测试时间保持固定。在这项工作中，我们通过一种自适应方法来挑战这一前提，用于语义分割，将推理过程调整为每个输入样本。自我适应在两个级别上运行。首先，它采用了自我监督的损失，该损失将网络中卷积层的参数定制为输入图像。其次，在批准层中，自适应近似于整个测试数据的平均值和方差，这是不可用的。它通过在训练和从单个测试样本得出的参考分布之间进行插值来实现这一目标。为了凭经验分析我们的自适应推理策略，我们制定并遵循严格的评估协议，以解决先前工作的严重局限性。我们的广泛分析得出了一个令人惊讶的结论：使用标准训练程序，自我适应大大优于强大的基准，并在多域基准测试方面设定了新的最先进的准确性。我们的研究表明，自适应推断可以补充培训时间的既定模型正规化实践，以改善深度网络的概括到异域数据。

无论是在功能选择的领域还是可解释的AI领域，都有基于其重要性的“排名”功能的愿望。然后可以将这种功能重要的排名用于：（1）减少数据集大小或（2）解释机器学习模型。但是，在文献中，这种特征排名没有以系统的，一致的方式评估。许多论文都有不同的方式来争论哪些具有重要性排名最佳的特征。本文通过提出一种新的评估方法来填补这一空白。通过使用合成数据集，可以事先知道特征重要性得分，从而可以进行更系统的评估。为了促进使用新方法的大规模实验，在Python建造了一个名为FSEVAL的基准测定框架。该框架允许并行运行实验，并在HPC系统上的计算机上分布。通过与名为“权重和偏见”的在线平台集成，可以在实时仪表板上进行交互探索图表。该软件作为开源软件发布，并在PYPI平台上以包裹发行。该研究结束时，探索了一个这样的大规模实验，以在许多方面找到参与算法的优势和劣势。

Continual Learning (CL) is a field dedicated to devise algorithms able to achieve lifelong learning. Overcoming the knowledge disruption of previously acquired concepts, a drawback affecting deep learning models and that goes by the name of catastrophic forgetting, is a hard challenge. Currently, deep learning methods can attain impressive results when the data modeled does not undergo a considerable distributional shift in subsequent learning sessions, but whenever we expose such systems to this incremental setting, performance drop very quickly. Overcoming this limitation is fundamental as it would allow us to build truly intelligent systems showing stability and plasticity. Secondly, it would allow us to overcome the onerous limitation of retraining these architectures from scratch with the new updated data. In this thesis, we tackle the problem from multiple directions. In a first study, we show that in rehearsal-based techniques (systems that use memory buffer), the quantity of data stored in the rehearsal buffer is a more important factor over the quality of the data. Secondly, we propose one of the early works of incremental learning on ViTs architectures, comparing functional, weight and attention regularization approaches and propose effective novel a novel asymmetric loss. At the end we conclude with a study on pretraining and how it affects the performance in Continual Learning, raising some questions about the effective progression of the field. We then conclude with some future directions and closing remarks.

域的概括（DG）研究了深度学习模型推广到训练分布的能力。在过去的十年中，文献已经大量填充了一系列培训方法，这些方法声称获得了更抽象和强大的数据表示以应对域的转移。最近的研究为DG提供了可再现的基准，指出了天真的经验风险最小化（ERM）对现有算法的有效性。然而，研究人员坚持使用相同过时的特征提取器，并且尚未注意不同骨干的影响。在本文中，我们从骨干开始，提出了对其内在概括能力的全面分析，迄今为止，研究界忽略了。我们评估了各种特征提取器，从标准残差解决方案到基于变压器的架构，发现大规模单域分类精度和DG功能之间的线性相关性。我们广泛的实验表明，通过采用竞争性骨干与有效的数据增强结合使用，普通ERM的表现优于最近的DG解决方案，并实现了最先进的准确性。此外，我们的其他定性研究表明，新型骨架提供了与同类样本更相似的表示，从而将特征空间中的不同域分开。这种概括能力的增强功能使DG算法的边缘空间为调查问题，提出了一个新的范式，将骨干放在聚光灯下，并鼓励在其顶部开发一致的算法。

域泛化算法使用来自多个域的培训数据来学习概括到未经识别域的模型。虽然最近提出的基准证明大多数现有算法不优于简单的基线，但建立的评估方法未能暴露各种因素的影响，这有助于性能不佳。在本文中，我们提出了一个域泛化算法的评估框架，其允许将误差分解成组件捕获概念的不同方面。通过基于域不变表示学习的思想的算法的普遍性的启发，我们扩展了评估框架，以捕获在实现不变性时捕获各种类型的失败。我们表明，泛化误差的最大贡献者跨越方法，数据集，正则化强度甚至培训长度各不相同。我们遵守与学习域不变表示的策略相关的两个问题。在彩色的MNIST上，大多数域泛化算法失败，因为它们仅在训练域上达到域名不变性。在Camelyon-17上，域名不变性会降低看不见域的表示质量。我们假设专注于在丰富的代表之上调整分类器可以是有希望的方向。

域泛化（DG）被认为是泛广泛化的前面。我们提出了经验证据表明，DG泛化的主要原因是训练时存在多个域。此外，我们表明IID中的泛化方法对DG的泛化同样重要。量身定制的方法未能在传统的DG（TDG）评估中增加性能增益。我们的实验提示如果TDG已经在评估ood泛化方面存在的有用性？为了进一步加强我们的调查，我们提出了一种新颖的评估策略，Classwise DG（CWDG），在这里，每个班级，我们随机选择一个域并将其保留在一边进行测试。我们认为，这项基准测试更接近人类学习，并在现实世界方案中相关。反直观地，尽管在培训期间暴露于所有域，但CWDG比TDG评估更具挑战性。在解释观察的同时，我们的作品在探索新想法之前，我们的作品在DG问题上进行了更重要的分析。

Neural image classifiers are known to undergo severe performance degradation when exposed to input that exhibits covariate-shift with respect to the training distribution. Successful hand-crafted augmentation pipelines aim at either approximating the expected test domain conditions or to perturb the features that are specific to the training environment. The development of effective pipelines is typically cumbersome, and produce transformations whose impact on the classifier performance are hard to understand and control. In this paper, we show that recent Text-to-Image (T2I) generators' ability to simulate image interventions via natural-language prompts can be leveraged to train more robust models, offering a more interpretable and controllable alternative to traditional augmentation methods. We find that a variety of prompting mechanisms are effective for producing synthetic training data sufficient to achieve state-of-the-art performance in widely-adopted domain-generalization benchmarks and reduce classifiers' dependency on spurious features. Our work suggests that further progress in T2I generation and a tighter integration with other research fields may represent a significant step towards the development of more robust machine learning systems.

研究兴趣大大增加了将数据驱动方法应用于力学问题的问题。尽管传统的机器学习（ML）方法已经实现了许多突破，但它们依赖于以下假设：培训（观察到的）数据和测试（看不见）数据是独立的且分布相同的（i.i.d）。因此，当应用于未知的测试环境和数据分布转移的现实世界力学问题时，传统的ML方法通常会崩溃。相反，分布（OOD）的概括假定测试数据可能会发生变化（即违反I.I.D.假设）。迄今为止，已经提出了多种方法来改善ML方法的OOD概括。但是，由于缺乏针对OOD回归问题的基准数据集，因此这些OOD方法在主导力学领域的回归问题上的效率仍然未知。为了解决这个问题，我们研究了机械回归问题的OOD泛化方法的性能。具体而言，我们确定了三个OOD问题：协变量移位，机制移位和采样偏差。对于每个问题，我们创建了两个基准示例，以扩展机械MNIST数据集收集，并研究了流行的OOD泛化方法在这些机械特定的回归问题上的性能。我们的数值实验表明，在大多数情况下，与传统的ML方法相比，在大多数情况下，在这些OOD问题上的传统ML方法的性能更好，但迫切需要开发更强大的OOD概括方法，这些方法在多个OOD场景中有效。总体而言，我们希望这项研究以及相关的开放访问基准数据集将进一步开发用于机械特定回归问题的OOD泛化方法。

Reliable application of machine learning-based decision systems in the wild is one of the major challenges currently investigated by the field. A large portion of established approaches aims to detect erroneous predictions by means of assigning confidence scores. This confidence may be obtained by either quantifying the model's predictive uncertainty, learning explicit scoring functions, or assessing whether the input is in line with the training distribution. Curiously, while these approaches all state to address the same eventual goal of detecting failures of a classifier upon real-life application, they currently constitute largely separated research fields with individual evaluation protocols, which either exclude a substantial part of relevant methods or ignore large parts of relevant failure sources. In this work, we systematically reveal current pitfalls caused by these inconsistencies and derive requirements for a holistic and realistic evaluation of failure detection. To demonstrate the relevance of this unified perspective, we present a large-scale empirical study for the first time enabling benchmarking confidence scoring functions w.r.t all relevant methods and failure sources. The revelation of a simple softmax response baseline as the overall best performing method underlines the drastic shortcomings of current evaluation in the abundance of publicized research on confidence scoring. Code and trained models are at https://github.com/IML-DKFZ/fd-shifts.

由于分布式概括是一个普遍不足的问题，因此在不同的研究计划中研究了各种代理目标（例如，校准，对抗性鲁棒性，算法腐败，跨轮班的不变性），导致不同的研究计划，从而提出不同的建议。在共享相同的抱负目标的同时，这些方法从未在相同的实验条件下对真实数据进行测试。在本文中，我们对以前的工作进行了统一的看法，突出了我们经验解决的消息差异，并提供有关如何衡量模型鲁棒性以及如何改进它的建议。为此，我们收集了172个公开可用的数据集对，用于培训和分布外评估准确性，校准错误，对抗性攻击，环境不变性和合成腐败。我们从九个不同的架构中的九个不同的架构中微调了31k网络。我们的发现证实，分布的精度往往会共同增加，但表明它们的关系在很大程度上取决于数据集依赖性，并且通常比以前较小的规模研究所提出的更加细微和更复杂。