我们通过直接重写其预测规则，介绍一种修改分类器的行为的方法。我们的方法几乎不需要额外的数据收集，可以应用于各种设置，包括将模型调整为新环境，并修改它以忽略杂散功能。我们的代码可在https://github.com/madrylab/editingclassifers获得。

State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any other visual concept. Learning directly from raw text about images is a promising alternative which leverages a much broader source of supervision. We demonstrate that the simple pre-training task of predicting which caption goes with which image is an efficient and scalable way to learn SOTA image representations from scratch on a dataset of 400 million (image, text) pairs collected from the internet. After pre-training, natural language is used to reference learned visual concepts (or describe new ones) enabling zero-shot transfer of the model to downstream tasks. We study the performance of this approach by benchmarking on over 30 different existing computer vision datasets, spanning tasks such as OCR, action recognition in videos, geo-localization, and many types of fine-grained object classification. The model transfers non-trivially to most tasks and is often competitive with a fully supervised baseline without the need for any dataset specific training. For instance, we match the accuracy of the original ResNet-50 on ImageNet zero-shot without needing to use any of the 1.28 million training examples it was trained on. We release our code and pre-trained model weights at https://github.com/OpenAI/CLIP.

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。

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.

We build new test sets for the CIFAR-10 and ImageNet datasets. Both benchmarks have been the focus of intense research for almost a decade, raising the danger of overfitting to excessively re-used test sets. By closely following the original dataset creation processes, we test to what extent current classification models generalize to new data. We evaluate a broad range of models and find accuracy drops of 3% -15% on CIFAR-10 and 11% -14% on ImageNet. However, accuracy gains on the original test sets translate to larger gains on the new test sets. Our results suggest that the accuracy drops are not caused by adaptivity, but by the models' inability to generalize to slightly "harder" images than those found in the original test sets.

剪辑的发展[Radford等，2021]引发了关于语言监督是否可以导致与传统仅图像方法更可转移表示的视觉模型的争论。我们的工作通过对两种方法的学习能力进行了对下游分类任务的学习能力进行仔细控制的比较来研究这个问题。我们发现，当预训练数据集符合某些标准时 - 它足够大，并且包含具有较低变异性的描述性字幕 - 仅图像的方法也与剪辑的传输性能不匹配，即使它们接受了更多图像数据的培训。但是，与人们期望的相反，在某些情况下，没有满足这些标准，其中通过标题增加的监督实际上是有害的。在我们的发现的激励下，我们设计了简单的处方，以使剪辑能够更好地利用现有预训练数据集中存在的语言信息。

为了改善模型概括，模型设计师通常会隐式或显式地限制其模型使用的功能。在这项工作中，我们通过将其视为数据的不同观点来探讨利用此类特征先验的设计空间。具体而言，我们发现经过多种功能先验训练的模型具有较少的重叠故障模式，因此可以更有效地组合。此外，我们证明，在其他（未标记的）数据上共同训练此类模型使他们能够纠正彼此的错误，这反过来又导致对虚假相关性的更好的概括和韧性。可在https://github.com/madrylab/copriors上找到代码

可以训练生成模型，以从特定域中生成图像，仅由文本提示引导，而不看到任何图像？换句话说：可以将图像生成器“盲目地训练”吗？利用大规模对比语言图像预训练（CLIP）模型的语义力量，我们提出了一种文本驱动方法，允许将生成模型转移到新域，而无需收集单个图像。我们展示通过自然语言提示和几分钟的培训，我们的方法可以通过各种风格和形状的多种域调整发电机。值得注意的是，许多这些修改难以与现有方法达到困难或完全不可能。我们在广泛的域中进行了广泛的实验和比较。这些证明了我们方法的有效性，并表明我们的移动模型保持了对下游任务吸引的生成模型的潜在空间属性。

在许多图像分类任务中，诸如夹子之类的开放式摄影模型具有高精度。但是，在某些设置中，他们的零拍摄性能远非最佳。我们研究模型修补程序，目的是提高对特定任务的准确性，而不会在表现已经足够的任务上降低准确性。为了实现这一目标，我们引入了油漆，这是一种修补方法，该方法在微调之前使用模型的权重与要修补的任务进行微调后的权重。在零机夹的性能差的九个任务上，油漆可将精度提高15至60个百分点，同时将ImageNet上的精度保留在零拍模型的一个百分点之内。油漆还允许在多个任务上修补单个模型，并通过模型刻度进行改进。此外，我们确定了广泛转移的案例，即使任务不相交，对一个任务进行修补也会提高其他任务的准确性。最后，我们研究了超出常见基准的应用程序，例如计数或减少印刷攻击对剪辑的影响。我们的发现表明，可以扩展一组任务集，开放式摄影模型可实现高精度，而无需从头开始重新训练它们。

可解释的人工智能（XAI）的新兴领域旨在为当今强大但不透明的深度学习模型带来透明度。尽管本地XAI方法以归因图的形式解释了个体预测，从而确定了重要特征的发生位置（但没有提供有关其代表的信息），但全局解释技术可视化模型通常学会的编码的概念。因此，两种方法仅提供部分见解，并留下将模型推理解释的负担。只有少数当代技术旨在将本地和全球XAI背后的原则结合起来，以获取更多信息的解释。但是，这些方法通常仅限于特定的模型体系结构，或对培训制度或数据和标签可用性施加其他要求，这实际上使事后应用程序成为任意预训练的模型。在这项工作中，我们介绍了概念相关性传播方法（CRP）方法，该方法结合了XAI的本地和全球观点，因此允许回答“何处”和“ where”和“什么”问题，而没有其他约束。我们进一步介绍了相关性最大化的原则，以根据模型对模型的有用性找到代表性的示例。因此，我们提高了对激活最大化及其局限性的共同实践的依赖。我们证明了我们方法在各种环境中的能力，展示了概念相关性传播和相关性最大化导致了更加可解释的解释，并通过概念图表，概念组成分析和概念集合和概念子区和概念子区和概念子集和定量研究对模型的表示和推理提供了深刻的见解。它们在细粒度决策中的作用。

Benchmark performance of deep learning classifiers alone is not a reliable predictor for the performance of a deployed model. In particular, if the image classifier has picked up spurious features in the training data, its predictions can fail in unexpected ways. In this paper, we develop a framework that allows us to systematically identify spurious features in large datasets like ImageNet. It is based on our neural PCA components and their visualization. Previous work on spurious features of image classifiers often operates in toy settings or requires costly pixel-wise annotations. In contrast, we validate our results by checking that presence of the harmful spurious feature of a class is sufficient to trigger the prediction of that class. We introduce a novel dataset "Spurious ImageNet" and check how much existing classifiers rely on spurious features.

这项调查回顾了对基于视觉的自动驾驶系统进行行为克隆训练的解释性方法。解释性的概念具有多个方面，并且需要解释性的驾驶强度是一种安全至关重要的应用。从几个研究领域收集贡献，即计算机视觉，深度学习，自动驾驶，可解释的AI（X-AI），这项调查可以解决几点。首先，它讨论了从自动驾驶系统中获得更多可解释性和解释性的定义，上下文和动机，以及该应用程序特定的挑战。其次，以事后方式为黑盒自动驾驶系统提供解释的方法是全面组织和详细的。第三，详细介绍和讨论了旨在通过设计构建更容易解释的自动驾驶系统的方法。最后，确定并检查了剩余的开放挑战和潜在的未来研究方向。

深层生成模型通过自动化基于收集的数据集的多样性，现实内容的综合，使新手用户更容易访问视觉内容。但是，当前的机器学习方法错过了创作过程的关键要素 - 综合远远超出数据分配和日常体验的东西的能力。为了开始解决此问题，我们可以通过仅编辑一些具有所需几何变化的原始模型输出来“扭曲”给定模型。我们的方法将低级更新应用于单个模型层以重建编辑的示例。此外，为了打击过度拟合，我们建议一种基于样式混合的潜在空间增强方法。我们的方法允许用户创建一个模型，该模型可以通过定义的几何更改合成无尽的对象，从而可以创建新的生成模型，而无需策划大规模数据集。我们还证明可以组成编辑的模型以实现汇总效果，并提出了一个交互式界面，以使用户能够通过组合创建新的模型。对多个测试案例的经验测量表明，我们方法对最近的GAN微调方法的优势。最后，我们使用编辑的模型展示了多个应用程序，包括潜在空间插值和图像编辑。

The ImageNet Large Scale Visual Recognition Challenge is a benchmark in object category classification and detection on hundreds of object categories and millions of images. The challenge has been run annually from 2010 to present, attracting participation from more than fifty institutions. This paper describes the creation of this benchmark dataset and the advances in object recognition that have been possible as a result. We discuss the chal-

我们表明，将人类的先验知识与端到端学习相结合可以通过引入基于零件的对象分类模型来改善深神经网络的鲁棒性。我们认为，更丰富的注释形式有助于指导神经网络学习更多可靠的功能，而无需更多的样本或更大的模型。我们的模型将零件分割模型与一个微小的分类器结合在一起，并经过训练的端到端，以同时将对象分割为各个部分，然后对分段对象进行分类。从经验上讲，与所有三个数据集的Resnet-50基线相比，我们的基于部分的模型既具有更高的精度和更高的对抗性鲁棒性。例如，鉴于相同的鲁棒性，我们部分模型的清洁准确性高达15个百分点。我们的实验表明，这些模型还减少了纹理偏见，并对共同的腐败和虚假相关性产生更好的鲁棒性。该代码可在https://github.com/chawins/adv-part-model上公开获得。

We present a framework for ranking images within their class based on the strength of spurious cues present. By measuring the gap in accuracy on the highest and lowest ranked images (we call this spurious gap), we assess spurious feature reliance for $89$ diverse ImageNet models, finding that even the best models underperform in images with weak spurious presence. However, the effect of spurious cues varies far more dramatically across classes, emphasizing the crucial, often overlooked, class-dependence of the spurious correlation problem. While most spurious features we observe are clarifying (i.e. improving test-time accuracy when present, as is typically expected), we surprisingly find many cases of confusing spurious features, where models perform better when they are absent. We then close the spurious gap by training new classification heads on lowly ranked (i.e. without common spurious cues) images, resulting in improved effective robustness to distribution shifts (ObjectNet, ImageNet-R, ImageNet-Sketch). We also propose a second metric to assess feature reliability, finding that spurious features are generally less reliable than non-spurious (core) ones, though again, spurious features can be more reliable for certain classes. To enable our analysis, we annotated $5,000$ feature-class dependencies over {\it all} of ImageNet as core or spurious using minimal human supervision. Finally, we show the feature discovery and spuriosity ranking framework can be extended to other datasets like CelebA and WaterBirds in a lightweight fashion with only linear layer training, leading to discovering a previously unknown racial bias in the Celeb-A hair classification.

The International Workshop on Reading Music Systems (WoRMS) is a workshop that tries to connect researchers who develop systems for reading music, such as in the field of Optical Music Recognition, with other researchers and practitioners that could benefit from such systems, like librarians or musicologists. The relevant topics of interest for the workshop include, but are not limited to: Music reading systems; Optical music recognition; Datasets and performance evaluation; Image processing on music scores; Writer identification; Authoring, editing, storing and presentation systems for music scores; Multi-modal systems; Novel input-methods for music to produce written music; Web-based Music Information Retrieval services; Applications and projects; Use-cases related to written music. These are the proceedings of the 3rd International Workshop on Reading Music Systems, held in Alicante on the 23rd of July 2021.

理解和解释训练有素的模型对许多机器学习目标至关重要，例如改善鲁棒性，解决概念漂移和减轻偏见。但是，这通常是一个临时过程，涉及手动查看许多测试样本上的模型的错误，并猜测这些错误的预测的根本原因。在本文中，我们提出了一种系统的方法，概念性的反事实解释（CCE），解释了为什么分类器在人类理解的概念方面在特定的测试样本上犯了一个错误（例如，此斑马被错误地分类为狗，因为因为是因为是因为是狗的。微弱的条纹）。我们基于两个先前的想法：反事实解释和概念激活向量，并在众所周知的预读模型上验证我们的方法，表明它有意义地解释了模型的错误。此外，对于接受具有虚假相关性数据的数据训练的新模型，CCE准确地将虚假相关性确定为单个错误分类测试样本中模型错误的原因。在两个具有挑战性的医学应用程序中，CCE产生了有用的见解，并由临床医生确认，涉及该模型在现实世界中犯的偏见和错误。

使用转移学习将预先训练的“源模型”调整为下游“目标任务”可以大大提高性能，而似乎没有缺点。在这项工作中，我们证明毕竟可能存在一个缺点：偏差转移或源模型偏见的趋势，即使将模型调整为目标类别后，也可以持续存在。通过合成和自然实验的组合，我们表明偏差转移（a）是在现实设置中（例如，在图像网或其他标准数据集上进行预训练时）以及（b）即使明确数据也可能发生（b） - 偏见。随着转移学习的模型越来越多地在现实世界中部署，我们的工作突出了理解预训练源模型的局限性的重要性。代码可从https://github.com/madrylab/bias-transfer获得

We study how robust current ImageNet models are to distribution shifts arising from natural variations in datasets. Most research on robustness focuses on synthetic image perturbations (noise, simulated weather artifacts, adversarial examples, etc.), which leaves open how robustness on synthetic distribution shift relates to distribution shift arising in real data. Informed by an evaluation of 204 ImageNet models in 213 different test conditions, we find that there is often little to no transfer of robustness from current synthetic to natural distribution shift. Moreover, most current techniques provide no robustness to the natural distribution shifts in our testbed. The main exception is training on larger and more diverse datasets, which in multiple cases increases robustness, but is still far from closing the performance gaps. Our results indicate that distribution shifts arising in real data are currently an open research problem. We provide our testbed and data as a resource for future work at https://modestyachts.github.io/imagenet-testbed/.