现有的方法用于隔离数据集中的硬群和虚假相关性通常需要人为干预。这可以使这些方法具有劳动密集型和特定于数据集的特定方式。为了解决这些缺点，我们提出了一种自动提炼模型故障模式的可扩展方法。具体而言，我们利用线性分类器来识别一致的误差模式，然后又诱导这些故障模式作为特征空间内的方向的自然表示。我们证明，该框架使我们能够发现并自动为培训数据集中的子群体提起挑战，并进行干预以改善模型对这些亚群的绩效。可在https://github.com/madrylab/failure-directions上找到代码

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.

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.

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

利用深度学习的最新进展，文本到图像生成模型目前具有吸引公众关注的优点。其中两个模型Dall-E 2和Imagen已经证明，可以从图像的简单文本描述中生成高度逼真的图像。基于一种称为扩散模型的新型图像生成方法，文本对图像模型可以生产许多不同类型的高分辨率图像，其中人类想象力是唯一的极限。但是，这些模型需要大量的计算资源来训练，并处理从互联网收集的大量数据集。此外，代码库和模型均未发布。因此，它可以防止AI社区尝试这些尖端模型，从而使其结果复制变得复杂，即使不是不可能。在本文中，我们的目标是首先回顾这些模型使用的不同方法和技术，然后提出我们自己的文本模型模型实施。高度基于DALL-E 2，我们引入了一些轻微的修改，以应对所引起的高计算成本。因此，我们有机会进行实验，以了解这些模型的能力，尤其是在低资源制度中。特别是，我们提供了比Dall-e 2的作者（包括消融研究）更深入的分析。此外，扩散模型使用所谓的指导方法来帮助生成过程。我们引入了一种新的指导方法，该方法可以与其他指导方法一起使用，以提高图像质量。最后，我们的模型产生的图像质量相当好，而不必维持最先进的文本对图像模型的重大培训成本。

Models trained via empirical risk minimization (ERM) are known to rely on spurious correlations between labels and task-independent input features, resulting in poor generalization to distributional shifts. Group distributionally robust optimization (G-DRO) can alleviate this problem by minimizing the worst-case loss over a set of pre-defined groups over training data. G-DRO successfully improves performance of the worst-group, where the correlation does not hold. However, G-DRO assumes that the spurious correlations and associated worst groups are known in advance, making it challenging to apply it to new tasks with potentially multiple unknown spurious correlations. We propose AGRO -- Adversarial Group discovery for Distributionally Robust Optimization -- an end-to-end approach that jointly identifies error-prone groups and improves accuracy on them. AGRO equips G-DRO with an adversarial slicing model to find a group assignment for training examples which maximizes worst-case loss over the discovered groups. On the WILDS benchmark, AGRO results in 8% higher model performance on average on known worst-groups, compared to prior group discovery approaches used with G-DRO. AGRO also improves out-of-distribution performance on SST2, QQP, and MS-COCO -- datasets where potential spurious correlations are as yet uncharacterized. Human evaluation of ARGO groups shows that they contain well-defined, yet previously unstudied spurious correlations that lead to model errors.

Standard training via empirical risk minimization (ERM) can produce models that achieve high accuracy on average but low accuracy on certain groups, especially in the presence of spurious correlations between the input and label. Prior approaches that achieve high worst-group accuracy, like group distributionally robust optimization (group DRO) require expensive group annotations for each training point, whereas approaches that do not use such group annotations typically achieve unsatisfactory worst-group accuracy. In this paper, we propose a simple two-stage approach, JTT, that first trains a standard ERM model for several epochs, and then trains a second model that upweights the training examples that the first model misclassified. Intuitively, this upweights examples from groups on which standard ERM models perform poorly, leading to improved worst-group performance. Averaged over four image classification and natural language processing tasks with spurious correlations, JTT closes 75% of the gap in worst-group accuracy between standard ERM and group DRO, while only requiring group annotations on a small validation set in order to tune hyperparameters.

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

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.

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。

Vision models often fail systematically on groups of data that share common semantic characteristics (e.g., rare objects or unusual scenes), but identifying these failure modes is a challenge. We introduce AdaVision, an interactive process for testing vision models which helps users identify and fix coherent failure modes. Given a natural language description of a coherent group, AdaVision retrieves relevant images from LAION-5B with CLIP. The user then labels a small amount of data for model correctness, which is used in successive retrieval rounds to hill-climb towards high-error regions, refining the group definition. Once a group is saturated, AdaVision uses GPT-3 to suggest new group descriptions for the user to explore. We demonstrate the usefulness and generality of AdaVision in user studies, where users find major bugs in state-of-the-art classification, object detection, and image captioning models. These user-discovered groups have failure rates 2-3x higher than those surfaced by automatic error clustering methods. Finally, finetuning on examples found with AdaVision fixes the discovered bugs when evaluated on unseen examples, without degrading in-distribution accuracy, and while also improving performance on out-of-distribution datasets.

在现实世界设置下自动发现视觉模型中的故障仍然是一个开放的挑战。这项工作说明了如何利用大量数据培训的现成，大规模，图像到文本和文本对象模型如何自动找到此类故障。本质上，有条件的文本到图像生成模型用于生成大量的合成，但现实的输入，给定了地面真相标签。错误分类的输入是聚类的，并使用字幕模型来描述每个群集。每个集群的描述依次使用来生成更多的输入，并评估特定簇是否会导致比预期更多的故障。我们使用该管道来证明我们可以有效地询问在Imagenet上训练的分类器以找到特定的故障案例并发现虚假相关性。我们还表明，我们可以扩展针对特定分类器体系结构的对抗数据集的方法。这项工作是概念验证，证明了大规模生成模型的实用性，以开放式方式自动发现视觉模型中的错误。我们还描述了与这种方法相关的许多局限性和陷阱。

Recent visuolinguistic pre-trained models show promising progress on various end tasks such as image retrieval and video captioning. Yet, they fail miserably on the recently proposed Winoground dataset, which challenges models to match paired images and English captions, with items constructed to overlap lexically but differ in meaning (e.g., "there is a mug in some grass" vs. "there is some grass in a mug"). By annotating the dataset using new fine-grained tags, we show that solving the Winoground task requires not just compositional language understanding, but a host of other abilities like commonsense reasoning or locating small, out-of-focus objects in low-resolution images. In this paper, we identify the dataset's main challenges through a suite of experiments on related tasks (probing task, image retrieval task), data augmentation, and manual inspection of the dataset. Our analysis suggests that a main challenge in visuolinguistic models may lie in fusing visual and textual representations, rather than in compositional language understanding. We release our annotation and code at https://github.com/ajd12342/why-winoground-hard .

Despite being responsible for state-of-the-art results in several computer vision and natural language processing tasks, neural networks have faced harsh criticism due to some of their current shortcomings. One of them is that neural networks are correlation machines prone to model biases within the data instead of focusing on actual useful causal relationships. This problem is particularly serious in application domains affected by aspects such as race, gender, and age. To prevent models from incurring on unfair decision-making, the AI community has concentrated efforts in correcting algorithmic biases, giving rise to the research area now widely known as fairness in AI. In this survey paper, we provide an in-depth overview of the main debiasing methods for fairness-aware neural networks in the context of vision and language research. We propose a novel taxonomy to better organize the literature on debiasing methods for fairness, and we discuss the current challenges, trends, and important future work directions for the interested researcher and practitioner.

鉴于部署更可靠的机器学习系统的重要性，研究界内的机器学习模型的解释性得到了相当大的关注。在计算机视觉应用中，生成反事实方法表示如何扰乱模型的输入来改变其预测，提供有关模型决策的详细信息。目前的方法倾向于产生关于模型决策的琐碎的反事实，因为它们通常建议夸大或消除所分类的属性的存在。对于机器学习从业者，这些类型的反事件提供了很少的价值，因为它们没有提供有关不期望的模型或数据偏差的新信息。在这项工作中，我们确定了琐碎的反事实生成问题，我们建议潜水以缓解它。潜水在使用多样性强制损失限制的解除印章潜在空间中学习扰动，以发现关于模型预测的多个有价值的解释。此外，我们介绍一种机制，以防止模型产生微不足道的解释。 Celeba和Synbols的实验表明，与先前的最先进的方法相比，我们的模型提高了生产高质量有价值解释的成功率。代码可在https://github.com/elementai/beyond- trial-explanations获得。

现代机器学习研究依赖于相对较少的精心策划数据集。即使在这些数据集中，通常在“不整合”或原始数据中，从业人员也面临着重要的数据质量和多样性问题，这些问题可能会非常强烈地解决。应对这些挑战的现有方法往往会对特定问题做出强烈的假设，并且通常需要先验知识或元数据，例如域标签。我们的工作与这些方法是正交的：相反，我们专注于为元数据考古学提供一个统一和有效的框架 - 在数据集中发现和推断示例的元数据。我们使用简单的转换策划了可能存在的数据集（例如，错误标记，非典型或过度分布示例）中可能存在的数据子集，并利用这些探针套件之间的学习动力学差异来推断感兴趣的元数据。我们的方法与跨不同任务的更复杂的缓解方法相提并论：识别和纠正标签错误的示例，对少数民族样本进行分类，优先考虑与培训相关的点并启用相关示例的可扩展人类审核。

机器学习模型通常会遇到与训练分布不同的样本。无法识别分布（OOD）样本，因此将该样本分配给课堂标签会显着损害模​​型的可靠性。由于其对在开放世界中的安全部署模型的重要性，该问题引起了重大关注。由于对所有可能的未知分布进行建模的棘手性，检测OOD样品是具有挑战性的。迄今为止，一些研究领域解决了检测陌生样本的问题，包括异常检测，新颖性检测，一级学习，开放式识别识别和分布外检测。尽管有相似和共同的概念，但分别分布，开放式检测和异常检测已被独立研究。因此，这些研究途径尚未交叉授粉，创造了研究障碍。尽管某些调查打算概述这些方法，但它们似乎仅关注特定领域，而无需检查不同领域之间的关系。这项调查旨在在确定其共同点的同时，对各个领域的众多著名作品进行跨域和全面的审查。研究人员可以从不同领域的研究进展概述中受益，并协同发展未来的方法。此外，据我们所知，虽然进行异常检测或单级学习进行了调查，但没有关于分布外检测的全面或最新的调查，我们的调查可广泛涵盖。最后，有了统一的跨域视角，我们讨论并阐明了未来的研究线，打算将这些领域更加紧密地融为一体。

最近已被证明扩散模型产生高质量的合成图像，尤其是与指导技术配对，以促进忠诚的多样性。我们探索文本条件图像综合问题的扩散模型，并比较了两种不同的指导策略：剪辑指导和自由分类指导。我们发现后者是人类评估者的优选，用于光敏和标题相似度，并且通常产生光素质拟种样品。使用自由分类指导的35亿参数文本条件扩散模型的样本由人类评估者对来自Dall-E的人的人们青睐，即使后者使用昂贵的剪辑重新划分。此外，我们发现我们的模型可以进行微调，以执行图像修复，从而实现强大的文本驱动的图像编辑。我们在过滤的数据集中培训较小的模型，并在https://github.com/openai/glide-text2im释放代码和权重。

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.

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.