Multi-modal image-text models such as CLIP and LiT have demonstrated impressive performance on image classification benchmarks and their zero-shot generalization ability is particularly exciting. While the top-5 zero-shot accuracies of these models are very high, the top-1 accuracies are much lower (over 25% gap in some cases). We investigate the reasons for this performance gap and find that many of the failure cases are caused by ambiguity in the text prompts. First, we develop a simple and efficient zero-shot post-hoc method to identify images whose top-1 prediction is likely to be incorrect, by measuring consistency of the predictions w.r.t. multiple prompts and image transformations. We show that our procedure better predicts mistakes, outperforming the popular max logit baseline on selective prediction tasks. Next, we propose a simple and efficient way to improve accuracy on such uncertain images by making use of the WordNet hierarchy; specifically we augment the original class by incorporating its parent and children from the semantic label hierarchy, and plug the augmentation into text promts. We conduct experiments on both CLIP and LiT models with five different ImageNet-based datasets. For CLIP, our method improves the top-1 accuracy by 17.13% on the uncertain subset and 3.6% on the entire ImageNet validation set. We also show that our method improves across ImageNet shifted datasets and other model architectures such as LiT. Our proposed method is hyperparameter-free, requires no additional model training and can be easily scaled to other large multi-modal architectures.

预训练的视觉模型（例如，剪辑）在许多下游任务中显示出有希望的零弹性概括，并具有正确设计的文本提示。最近的作品不依赖手工设计的提示，而是使用下游任务的培训数据来学习提示。虽然有效，但针对领域数据的培训却降低了模型的概括能力，使其无法看到新领域。在这项工作中，我们提出了测试时间提示调整（TPT），该方法可以通过单个测试样本即时学习自适应提示。对于图像分类，TPT通过使用置信度选择最小化熵来优化提示，以便模型在每个测试样本的不同增强视图上都具有一致的预测。在评估对自然分布变化的概括时，TPT平均将零击的TOP-1精度提高了3.6％，超过了先前需要其他特定于任务的训练数据的迅速调整方法。在评估看不见类别的跨数据集泛化时，TPT与使用其他培训数据的最先进方法相当。项目页面：https：//azshue.github.io/tpt。

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.

诸如剪辑之类的大型预训练的视觉模型在学习表现方面表现出巨大的潜力，这些模型可以在各种下游任务中转移。与主要基于离散标签的传统表示学习不同，视觉语言预训练会使图像和文本在公共特征空间中对齐，这允许通过提示零弹性转移到下游任务，即从分类权重合成。描述兴趣类的自然语言。在这项工作中，我们表明，在实践中部署此类模型的一个重大挑战是及时的工程，它需要域专业知识，并且非常耗时 - 由于措辞的略有变化，需要花费大量时间来进行单词调整可能会对性能产生巨大影响。受到自然语言处理（NLP）迅速学习研究的最新进展的启发，我们提出了上下文优化（COP），这是一种专门用于调整类似剪辑的视觉语言模型的简单方法，用于下游图像识别。具体而言，Coop用可学习的向量建模了提示A的上下文单词，而整个预训练的参数则保持固定。为了处理不同的图像识别任务，我们提供了两个COOP的实现：统一上下文和特定于班级的上下文。通过在11个数据集上进行的大量实验，我们证明Coop只需要一两个镜头才能以相当的利润击败手工制作的提示，并且能够以16张镜头（例如16张照片）获得迅速工程的显着改进增益约为15％（最高达到45％以上）。尽管是一种基于学习的方法，但与使用手工制作的提示相比，Coop与零拍模型相比，取得了出色的域泛化性能。

Contrastive Language-Image Pre-training (CLIP) has emerged as a simple yet effective way to train large-scale vision-language models. CLIP demonstrates impressive zero-shot classification and retrieval on diverse downstream tasks. However, to leverage its full potential, fine-tuning still appears to be necessary. Fine-tuning the entire CLIP model can be resource-intensive and unstable. Moreover, recent methods that aim to circumvent this need for fine-tuning still require access to images from the target distribution. In this paper, we pursue a different approach and explore the regime of training-free "name-only transfer" in which the only knowledge we possess about the downstream task comprises the names of downstream target categories. We propose a novel method, SuS-X, consisting of two key building blocks -- SuS and TIP-X, that requires neither intensive fine-tuning nor costly labelled data. SuS-X achieves state-of-the-art zero-shot classification results on 19 benchmark datasets. We further show the utility of TIP-X in the training-free few-shot setting, where we again achieve state-of-the-art results over strong training-free baselines. Code is available at https://github.com/vishaal27/SuS-X.

自从出现以来，在大型，随机收集的数据上训练的视觉模型在许多领域都有重大影响。但是，由于它们在各个领域表现出色，例如图像文本 - 取回，因此他们的内部工作仍未得到充分了解。当前的工作分析了这些模型的真实零击功能。我们从分析培训语料库的分析开始，评估测试类的程度（以及哪个）实际上是零射击，以及与单个类别的性能如何相关。我们跟进这些模型的基于属性的零击学习能力的分析，以评估这种经典的零击概念从大规模的监督中出现的方式。我们利用最近发布的LAION400M数据语料库以及公开可用的剪辑，OpenClip和Flava的模型，评估了基于属性的CUB和AWA2基准的零摄影功能。我们的分析表明：（i）在预训练期间（很多）观察到大多数流行的零射门基准中的大多数类别； （ii）零射击性能主要来自模型识别类标签的能力，每当它们存在于文本中时，并且只有在不使用类标签时才能观察到基于属性的zeroshot学习的较低的性能能力； （iii）所使用的属性数量可能会对性能产生重大影响，并且很容易导致大幅下降。

Prompt tuning is a new few-shot transfer learning technique that only tunes the learnable prompt for pre-trained vision and language models such as CLIP. However, existing prompt tuning methods tend to learn spurious or entangled representations, which leads to poor generalization to unseen concepts. Towards non-spurious and efficient prompt learning from limited examples, this paper presents a novel \underline{\textbf{C}}ounterfactual \underline{\textbf{P}}rompt \underline{\textbf{L}}earning (CPL) method for vision and language models, which simultaneously employs counterfactual generation and contrastive learning in a joint optimization framework. Particularly, CPL constructs counterfactual by identifying minimal non-spurious feature change between semantically-similar positive and negative samples that causes concept change, and learns more generalizable prompt representation from both factual and counterfactual examples via contrastive learning. Extensive experiments demonstrate that CPL can obtain superior few-shot performance on different vision and language tasks than previous prompt tuning methods on CLIP. On image classification, we achieve 3.55\% average relative improvement on unseen classes across seven datasets; on image-text retrieval and visual question answering, we gain up to 4.09\% and 25.08\% relative improvements across three few-shot scenarios on unseen test sets respectively.

Contrastive Language-Image Pre-trained (CLIP) models have zero-shot ability of classifying an image belonging to "[CLASS]" by using similarity between the image and the prompt sentence "a [CONTEXT] of [CLASS]". Based on exhaustive text cues in "[CONTEXT]", CLIP model is aware of different contexts, e.g. background, style, viewpoint, and exhibits unprecedented robustness against a wide range of distribution shifts. However, recent works find further fine-tuning of CLIP models improves accuracy but sacrifices the robustness on downstream tasks. We conduct an empirical investigation to show fine-tuning will corrupt the context-aware ability of pre-trained CLIP features. To solve this problem, we propose Context-Aware Robust Fine-tuning (CAR-FT). CAR-FT regularizes the model during fine-tuning to capture the context information. Specifically, we use zero-shot prompt weights to get the context distribution contained in the image. By minimizing the Kullback-Leibler Divergence (KLD) between context distributions induced by original/fine-tuned CLIP models, CAR-FT makes the context-aware ability of CLIP inherited into downstream tasks, and achieves both higher In-Distribution (ID) and Out-Of-Distribution (OOD) accuracy. The experimental results show CAR-FT achieves superior robustness on five OOD test datasets of ImageNet, and meanwhile brings accuracy gains on nine downstream tasks. Additionally, CAR-FT surpasses previous Domain Generalization (DG) methods and gets 78.5% averaged accuracy on DomainBed benchmark, building the new state-of-the-art.

我们研究了很少的细粒实体键入（FET）的问题，其中只有几个带注释的实体对每种实体类型提供了上下文。最近，基于及时的调整通过将实体类型分类任务作为“填补空白”的问题来表明在几次射击方案中表现出优越的性能。这允许有效利用预训练的语言模型（PLM）的强语建模能力。尽管当前基于及时的调整方法成功了，但仍有两个主要挑战：（1）提示中的口头化器要么是由外部知识基础手动设计或构建的，而无需考虑目标语料库和标签层次结构信息，而且（2）当前方法主要利用PLM的表示能力，但没有通过广泛的通用域预训练来探索其产生的功率。在这项工作中，我们为由两个模块组成的几个弹药fet提出了一个新颖的框架：（1）实体类型标签解释模块自动学习将类型标签与词汇联系起来，通过共同利用几个播放实例和标签层次结构和标签层次结构，以及（2）基于类型的上下文化实例生成器根据给定实例生成新实例，以扩大培训集以更好地概括。在三个基准数据集上，我们的模型优于大量利润的现有方法。可以在https://github.com/teapot123/fine-graining-entity-typing上找到代码。

Incidental supervision from language has become a popular approach for learning generic visual representations that can be prompted to perform many recognition tasks in computer vision. We conduct an in-depth exploration of the CLIP model and show that its visual representation is often strongly biased towards solving some tasks more than others. Moreover, which task the representation will be biased towards is unpredictable, with little consistency across images. To resolve this task bias, we show how to learn a visual prompt that guides the representation towards features relevant to their task of interest. Our results show that these visual prompts can be independent of the input image and still effectively provide a conditioning mechanism to steer visual representations towards the desired task.

在低标签制度中，解决图像的多标签识别（MLR）是许多现实世界应用的一项艰巨任务。最近的工作学会了文本和视觉空间之间的一致性，以补偿图像标签不足，但由于可用的MLR注释量有限，因此失去了准确性。在这项工作中，我们利用数百万辅助图像文本对预测的文本和视觉特征的牢固对齐，并提出双背景优化（dualCoop）作为部分标签MLR和零发射MLR的统一框架。 DualCoop用类名来编码正面和负面的上下文，作为语言输入的一部分（即提示）。由于DualCoop仅在验证的视觉语言框架上引入了非常轻松的开销，因此它可以迅速适应具有有限的注释甚至看不见的类别的多标签识别任务。对两个挑战性低标签设置的标准多标签识别基准测试的实验证明了我们方法比最新方法的优势。

Prompt tuning has been employed as an efficient way to adapt large vision-language pre-trained models (e.g. CLIP) to various downstream tasks in data-limited or label-limited settings. Nonetheless, visual data (e.g., images) is by default prerequisite for learning prompts in existing methods. In this work, we advocate that the effectiveness of image-text contrastive learning in aligning the two modalities (for training CLIP) further makes it feasible to treat texts as images for prompt tuning and introduce TaI prompting. In contrast to the visual data, text descriptions are easy to collect, and their class labels can be directly derived. Particularly, we apply TaI prompting to multi-label image recognition, where sentences in the wild serve as alternatives to images for prompt tuning. Moreover, with TaI, double-grained prompt tuning (TaI-DPT) is further presented to extract both coarse-grained and fine-grained embeddings for enhancing the multi-label recognition performance. Experimental results show that our proposed TaI-DPT outperforms zero-shot CLIP by a large margin on multiple benchmarks, e.g., MS-COCO, VOC2007, and NUS-WIDE, while it can be combined with existing methods of prompting from images to improve recognition performance further. Code is released at https://github.com/guozix/TaI-DPT.

开放词汇模型是图像分类的有希望的新范式。与传统的分类模型不同，开放词汇模型在推理过程中用自然语言指定的任何任意类别中分类。这种称为“提示”的自然语言通常由一组手写的模板（例如，“ {}”的照片）组成，这些模板与每个类别名称完成。这项工作引入了一种简单的方法，可以生成更高的准确性提示，而无需对图像域的明确知识和更少的手工构造句子。为了实现这一目标，我们将开放式词汇模型与大语言模型（LLMS）相结合，以通过语言模型（Cupl，发音为“夫妇”）创建自定义提示。特别是，我们利用LLMS中包含的知识来生成许多针对每个对象类别定制的描述性句子。我们发现，这种直接和一般的方法可提高一系列零照片分类基准的准确性，包括ImageNet上超过一个百分比的增益。最后，此方法不需要额外的培训，并且仍然完全零射。代码可在https://github.com/sarahpratt/cupl上找到。

随着大型预训练的Vison语言模型（如剪辑）的出现，可以通过及时调整来调整可转让表示形式。及时调整试图从存储在预训练的视觉模型的图像和文本编码器中的常识中探索有益信息，以探索下游任务。最近提出的名为“上下文优化”（COP）的方法将一组可学习的向量从语言侧引入文本提示符，而单独调整文本提示符则不会影响图像编码器的计算视觉特征，从而导致了次级优势。在本文中，我们通过学习文本提示并同时为文本和图像编码器提供双重模式提示调整范式。此外，为了使视觉提示更多地集中在目标视觉概念上，我们提出了类感知的视觉及时调整（CAVPT），该调整是通过在模板提示和视觉类别令牌嵌入的语言描述之间进行交叉注意来动态生成的。我们的方法提供了一种新的范式来调整大型预训练的视觉模型，并在8个数据集上进行了广泛的实验结果，证明了该方法的有效性。我们的代码在补充材料中可用。

对比训练有素的语言图像模型，例如剪辑，Align和Basic，已经证明了对多种具有挑战性的自然分配变化的前所未有的鲁棒性。由于这些语言图像模型与以前的培训方法有多种不同，因此一个重要的问题是导致稳定性增长的原因。我们通过系统的实验研究回答这个问题。具体而言，我们研究了鲁棒性增长的五个不同可能的原因：（i）训练集大小，（ii）培训分配，（iii）在培训时进行语言监督，（iv）测试时语言监督，以及（v）对比损失函数。我们的实验表明，更多样化的训练分布是稳健性增长的主要原因，其他因素几乎没有稳健性。除了实验结果之外，我们还引入了Imagenet捕获，这是一种来自Flickr的原始文本注释的Imagenet版本，以实现语言图像训练的进一步受控实验。

最近，Vision-Language预训练的零拍图像分类已经表现出令人难以置信的成就，即该模型可以对任意类别进行分类而不看到该类别的其他注释图像。然而，目前尚不清楚如何在更广泛的视觉问题上进行零射识别，例如对象检测和语义分割。在本文中，我们通过在现成的预训练的视觉模型，即剪辑上建立零拍语义分割来定位零拍语义分割。很难因为语义分割和剪辑模型在不同的视觉粒度上执行，该语义分段处理在像素上时，而剪辑在图像上执行。为了解决处理粒度的差异，我们拒绝使用普遍的一级FCN基于FCN的框架，并倡导一个两级语义分割框架，其中第一阶段提取一个完全提取的掩模提案和第二阶段利用基于图像的剪辑模型在第一阶段生成的蒙版图像作物上执行零拍分类。我们的实验结果表明，这种简单的框架通过大型利润率超越了先前的最先进：+29.5 Hiou On Pascal VOC 2012 DataSet，+8.9 Hiou On Coco Stuff DataSet。凭借其简单性和强大的表现，我们希望本框架成为促进未来研究的基准。

通过使用图像文本匹配模型的使用，零光学习在计算机视觉中的应用已彻底改变。最值得注意的示例，剪辑，已广泛用于带有文本提示的零摄像分类和指导生成模型。但是，对于输入文本的措辞，夹子的零拍情况不稳定，因此有必要仔细设计所用的提示。我们发现这种不稳定性源于选择性相似性分数，该得分仅基于语义上有意义的输入令牌的子集。为了减轻它，我们提出了一种新颖的基于可解释的方法，该方法增加了损失术语，以确保剪辑专注于输入的所有相关语义部分，此外还采用了以前的作品中使用的夹子相似性损失。当通过及时的工程应用于单发分类时，我们的方法可以提高识别率，而无需进行额外的培训或微调。此外，我们表明使用我们的方法对生成模型的剪辑指导显着改善了生成的图像。最后，我们通过在对象位置进行空间条件来证明对基于文本的图像生成的新颖使用，这是需要将图像解释性热图限制在预定的边界框中。

We introduce Patch Aligned Contrastive Learning (PACL), a modified compatibility function for CLIP's contrastive loss, intending to train an alignment between the patch tokens of the vision encoder and the CLS token of the text encoder. With such an alignment, a model can identify regions of an image corresponding to a given text input, and therefore transfer seamlessly to the task of open vocabulary semantic segmentation without requiring any segmentation annotations during training. Using pre-trained CLIP encoders with PACL, we are able to set the state-of-the-art on the task of open vocabulary zero-shot segmentation on 4 different segmentation benchmarks: Pascal VOC, Pascal Context, COCO Stuff and ADE20K. Furthermore, we show that PACL is also applicable to image-level predictions and when used with a CLIP backbone, provides a general improvement in zero-shot classification accuracy compared to CLIP, across a suite of 12 image classification datasets.

Stylegan的成功使得在合成和真实图像上启用了前所未有的语义编辑能力。然而，这种编辑操作要么是使用人类指导的语义监督或描述的培训。在另一个开发中，剪辑架构已被互联网级图像和文本配对培训，并且已被示出在几个零拍摄学习设置中有用。在这项工作中，我们调查了如何有效地链接样式登录和剪辑的预训练潜空间，这反过来允许我们从Stylegan，查找和命名有意义的编辑操作自动提取语义标记的编辑方向，而无需任何额外的人类指导。从技术上讲，我们提出了两块新颖的建筑块;一个用于查找有趣的夹子方向，一个用于在CLIP潜在空间中标记任意方向。安装程序不假设任何预定的标签，因此我们不需要任何其他监督文本/属性来构建编辑框架。我们评估所提出的方法的有效性，并证明了解标记标记的样式编辑方向的提取确实可能，并揭示了有趣和非琐碎的编辑方向。

我们在本文中解决的主要问题是如何扩展对看不见类（也称为零局学习）的视觉识别，以达到成千上万的类别，如Imagenet-21K基准中。在这个规模上，尤其是ImageNet-21K中包含许多细粒类别的规模，学习质量的视觉语义表示至关重要，它们具有足够的歧视性，足以识别看不见的类别并将其与见证的类别区分开来。我们提出了一个\ emph {h} ierarchical \ emph {g} raphical知识\ emph {r}基于置信度的分类方法（被称为HGR-net）的EPRESENTATION框架。我们的实验结果表明，HGR-NET可以利用层次结构概念知识来掌握类遗传关系。与Imagenet-21K基准的亚军方法相比，我们的方法大大优于所有现有技术，使性能提高了7 \％。我们表明，HGR-NET在几个场景中学习有效。我们还分析了较小的数据集（例如ImageNet-21K-P，2-s-s和3-shops）的方法，证明了其泛化能力。我们的基准和代码可在https://kaiyi.me/p/hgrnet.html上获得。