Pretrained large-scale vision-language models like CLIP have exhibited strong generalization over unseen tasks. Yet imperceptible adversarial perturbations can significantly reduce CLIP's performance on new tasks. In this work, we identify and explore the problem of \emph{adapting large-scale models for zero-shot adversarial robustness}. We first identify two key factors during model adaption -- training losses and adaptation methods -- that affect the model's zero-shot adversarial robustness. We then propose a text-guided contrastive adversarial training loss, which aligns the text embeddings and the adversarial visual features with contrastive learning on a small set of training data. We apply this training loss to two adaption methods, model finetuning and visual prompt tuning. We find that visual prompt tuning is more effective in the absence of texts, while finetuning wins in the existence of text guidance. Overall, our approach significantly improves the zero-shot adversarial robustness over CLIP, seeing an average improvement of over 31 points over ImageNet and 15 zero-shot datasets. We hope this work can shed light on understanding the zero-shot adversarial robustness of large-scale models.

Prompt Tuning, conditioning on task-specific learned prompt vectors, has emerged as a data-efficient and parameter-efficient method for adapting large pretrained vision-language models to multiple downstream tasks. However, existing approaches usually consider learning prompt vectors for each task independently from scratch, thereby failing to exploit the rich shareable knowledge across different vision-language tasks. In this paper, we propose multitask vision-language prompt tuning (MVLPT), which incorporates cross-task knowledge into prompt tuning for vision-language models. Specifically, (i) we demonstrate the effectiveness of learning a single transferable prompt from multiple source tasks to initialize the prompt for each target task; (ii) we show many target tasks can benefit each other from sharing prompt vectors and thus can be jointly learned via multitask prompt tuning. We benchmark the proposed MVLPT using three representative prompt tuning methods, namely text prompt tuning, visual prompt tuning, and the unified vision-language prompt tuning. Results in 20 vision tasks demonstrate that the proposed approach outperforms all single-task baseline prompt tuning methods, setting the new state-of-the-art on the few-shot ELEVATER benchmarks and cross-task generalization benchmarks. To understand where the cross-task knowledge is most effective, we also conduct a large-scale study on task transferability with 20 vision tasks in 400 combinations for each prompt tuning method. It shows that the most performant MVLPT for each prompt tuning method prefers different task combinations and many tasks can benefit each other, depending on their visual similarity and label similarity. Code is available at https://github.com/sIncerass/MVLPT.

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。

Finetuning image-text models such as CLIP achieves state-of-the-art accuracies on a variety of benchmarks. However, recent works like WiseFT (Wortsman et al., 2021) and LP-FT (Kumar et al., 2022) have shown that even subtle differences in the finetuning process can lead to surprisingly large differences in the final performance, both for in-distribution (ID) and out-of-distribution (OOD) data. In this work, we show that a natural and simple approach of mimicking contrastive pretraining consistently outperforms alternative finetuning approaches. Specifically, we cast downstream class labels as text prompts and continue optimizing the contrastive loss between image embeddings and class-descriptive prompt embeddings (contrastive finetuning). Our method consistently outperforms baselines across 7 distribution shifts, 6 transfer learning, and 3 few-shot learning benchmarks. On WILDS-iWILDCam, our proposed approach FLYP outperforms the top of the leaderboard by $2.3\%$ ID and $2.7\%$ OOD, giving the highest reported accuracy. Averaged across 7 OOD datasets (2 WILDS and 5 ImageNet associated shifts), FLYP gives gains of $4.2\%$ OOD over standard finetuning and outperforms the current state of the art (LP-FT) by more than $1\%$ both ID and OOD. Similarly, on 3 few-shot learning benchmarks, our approach gives gains up to $4.6\%$ over standard finetuning and $4.4\%$ over the state of the art. In total, these benchmarks establish contrastive finetuning as a simple, intuitive, and state-of-the-art approach for supervised finetuning of image-text models like CLIP. Code is available at https://github.com/locuslab/FLYP.

Vision-language foundation models pretrained on large-scale data provide a powerful tool for many visual understanding tasks. Notably, many vision-language models build two encoders (visual and textual) that can map two modalities into the same embedding space. As a result, the learned representations achieve good zero-shot performance on tasks like image classification. However, when there are only a few examples per category, the potential of large vision-language models is often underperformed, mainly due to the gap between a large number of parameters and a relatively small amount of training data. This paper shows that we can significantly improve the performance of few-shot classification by using the category names to initialize the classification head. More interestingly, we can borrow the non-perfect category names, or even names from a foreign language, to improve the few-shot classification performance compared with random initialization. With the proposed category name initialization method, our model obtains the state-of-the-art performance on a number of few-shot image classification benchmarks (e.g., 87.37\% on ImageNet and 96.08\% on Stanford Cars, both using five-shot learning). We also investigate and analyze when the benefit of category names diminishes and how to use distillation to improve the performance of smaller models, providing guidance for future research.

This paper presents a simple and effective visual prompting method for adapting pre-trained models to downstream recognition tasks. Our method includes two key designs. First, rather than directly adding together the prompt and the image, we treat the prompt as an extra and independent learnable component. We show that the strategy of reconciling the prompt and the image matters, and find that warping the prompt around a properly shrinked image empirically works the best. Second, we re-introduce two "old tricks" commonly used in building transferable adversarial examples, i.e., input diversity and gradient normalization, into visual prompting. These techniques improve optimization and enable the prompt to generalize better. We provide extensive experimental results to demonstrate the effectiveness of our method. Using a CLIP model, our prompting method sets a new record of 82.8% average accuracy across 12 popular classification datasets, substantially surpassing the prior art by +5.6%. It is worth noting that this prompting performance already outperforms linear probing by +2.1% and can even match fully fine-tuning in certain datasets. In addition, our prompting method shows competitive performance across different data scales and against distribution shifts. The code is publicly available at https://github.com/UCSC-VLAA/EVP.

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。

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。

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 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.

制作对抗性攻击的大多数方法都集中在具有单个主体对象的场景上（例如，来自Imagenet的图像）。另一方面，自然场景包括多个在语义上相关的主要对象。因此，探索设计攻击策略至关重要，这些攻击策略超出了在单对象场景上学习或攻击单对象受害者分类器。由于其固有的属性将扰动向未知模型的强大可传递性强，因此本文介绍了使用生成模型对多对象场景的对抗性攻击的第一种方法。为了代表输入场景中不同对象之间的关系，我们利用开源的预训练的视觉语言模型剪辑（对比语言图像 - 预训练），并动机利用语言中的编码语义来利用编码的语义空间与视觉空间一起。我们称这种攻击方法生成对抗性多对象场景攻击（GAMA）。 GAMA展示了剪辑模型作为攻击者的工具的实用性，以训练可强大的扰动发电机为多对象场景。使用联合图像文本功能来训练发电机，我们表明GAMA可以在各种攻击环境中制作有效的可转移扰动，以欺骗受害者分类器。例如，GAMA触发的错误分类比在黑框设置中的最新生成方法高出约16％，在黑框设置中，分类器体系结构和攻击者的数据分布都与受害者不同。我们的代码将很快公开提供。

对比度学习（CL）可以通过在其顶部的线性分类器上学习更广泛的特征表示并实现下游任务的最先进的性能。然而，由于对抗性稳健性在图像分类中变得至关重要，但仍然不清楚CL是否能够为下游任务保留鲁棒性。主要挑战是，在自我监督的预押率+监督的FineTuning范式中，由于学习任务不匹配从预先追溯到Fineetuning，对抗性鲁棒性很容易被遗忘。我们称之为挑战“跨任务稳健性转移性”。为了解决上述问题，在本文中，我们通过稳健性增强的镜头重新审视并提前CL原理。我们展示了（1）对比视图的设计事项：图像的高频分量有利于提高模型鲁棒性; （2）使用伪监督刺激（例如，诉诸特征聚类）增强CL，有助于保持稳健性而不会忘记。配备了我们的新设计，我们提出了一种新的对抗对比预制框架的advcl。我们表明Advcl能够增强跨任务稳健性转移性，而不会损失模型精度和芬降效率。通过彻底的实验研究，我们展示了Advcl优于跨多个数据集（CiFar-10，CiFar-100和STL-10）和FineTuning方案的最先进的自我监督的自我监督学习方法（线性评估和满模型fineetuning）。

探索大规模预处理的基础模型对计算机视觉具有重大兴趣，因为这些模型可以快速转移到许多下游任务中。本文介绍了对比字幕（COCA），这是一种极简主义的设计，旨在为图像文本编码器编码器基础模型预算与对比度损失和字幕损失，从而从剪辑和诸如simvlm之类的生成方法之类的对比方法中包含模型能力。与所有解码器层都参与编码器输出的标准编码器 - 模块变压器相反，可口可乐省略了解码器层的上半部分的交叉注意，以编码单峰文本表示，并串联到剩余的解码器层，这些解码器与图像编码器相交的解码器层多模式图像文本表示。除了对多模态解码器输出的字幕损失外，我们还应用了单峰图像和文本嵌入之间的对比损失，该输出可以预测文本令牌自动加压。通过共享相同的计算图，可以用最小的开销有效地计算两个培训目标。可口可乐是端到端和从头开始的网络尺度alt-text数据和带注释的图像，通过将所有标签视为文本，无缝地统一自然语言监督以进行表示。从经验上讲，可口可乐通过零拍传输或在广泛的下游任务上进行零摄像转移或最少的特定任务适应，跨越视觉识别（Imagenet，Kinetics-400/600/700，瞬间， ），交叉模式检索（MSCOCO，FLICKR30K，MSR-VTT），多模式理解（VQA，SNLI-VE，NLVR2）和图像字幕（MSCOCO，NOCAPS）。值得注意的是，在Imagenet分类方面，COCA获得了86.3％的TOP-1准确性，带有冷冻编码器和学习的分类头90.6％，以及带有填充编码器的Imagenet上的新最先进的91.0％Top-1 Top-1精度。

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.

Many visual recognition models are evaluated only on their classification accuracy, a metric for which they obtain strong performance. In this paper, we investigate whether computer vision models can also provide correct rationales for their predictions. We propose a ``doubly right'' object recognition benchmark, where the metric requires the model to simultaneously produce both the right labels as well as the right rationales. We find that state-of-the-art visual models, such as CLIP, often provide incorrect rationales for their categorical predictions. However, by transferring the rationales from language models into visual representations through a tailored dataset, we show that we can learn a ``why prompt,'' which adapts large visual representations to produce correct rationales. Visualizations and empirical experiments show that our prompts significantly improve performance on doubly right object recognition, in addition to zero-shot transfer to unseen tasks and datasets.

虽然大型审计的基础模型（FMS）对数据集级别的分布变化显示出显着的零击分类鲁棒性，但它们对亚群或组移动的稳健性相对却相对不受欢迎。我们研究了这个问题，并发现诸如剪辑之类的FMS可能对各种群体转移可能不健壮。在9个稳健性基准中，其嵌入式分类零射击分类导致平均和最差组精度之间的差距高达80.7个百分点（PP）。不幸的是，现有的改善鲁棒性的方法需要重新培训，这在大型基础模型上可能非常昂贵。我们还发现，改善模型推理的有效方法（例如，通过适配器，具有FM嵌入式作为输入的轻量级网络）不会持续改进，有时与零击相比会伤害组鲁棒性（例如，将精度差距提高到50.1 pp on 50.1 pp on On on 50.1 pp on Celeba）。因此，我们制定了一种适配器培训策略，以有效有效地改善FM组的鲁棒性。我们激励的观察是，尽管同一阶级中的群体中较差的鲁棒性在基础模型“嵌入空间”中分开，但标准适配器训练可能不会使这些要点更加紧密。因此，我们提出了对比度的适应，该适应器会通过对比度学习进行训练适配器，以使样品嵌入在同一类中的地面真相类嵌入和其他样品嵌入。在整个9个基准测试中，我们的方法始终提高组鲁棒性，使最差的组精度提高了8.5至56.0 pp。我们的方法也是有效的，这样做的方法也没有任何FM芬太尼，只有一组固定的冷冻FM嵌入。在水鸟和Celeba等基准上，这导致最差的组精度可与最先进的方法相媲美，而最先进的方法可以重新训练整个模型，而仅训练$ \ leq $ 1％的模型参数。

从自然语言监督中学习视觉表示，最近在许多开创性的作品中表现出了巨大的希望。通常，这些具有语言的视觉模型表现出对各种数据集和任务的强大可传递性。但是，由于缺乏易于使用的评估工具包和公共基准，评估这些模型的可转让性仍然很具有挑战性。为了解决这个问题，我们构建了高级版（评估语言的视觉任务级传输），这是用于评估（预训练）语言增强视觉模型的第一个基准和工具包。升华由三个组成部分组成。 （i）数据集。作为下游评估套件，它由20个图像分类数据集和35个对象检测数据集组成，每个数据集都用外部知识来增强。 （ii）工具包。开发了自动高参数调谐工具包，以促进下游任务的模型评估。 （iii）指标。多种评估指标用于测量样品效率（零射击和少量）和参数效率（线性探测和完整模型微调）。我们在https://computer-vision-in-the-wild.github.io/elevater/上公开发布leverater

Large-scale multi-modal training with image-text pairs imparts strong generalization to CLIP model. Since training on a similar scale for videos is infeasible, recent approaches focus on the effective transfer of image-based CLIP to the video domain. In this pursuit, new parametric modules are added to learn temporal information and inter-frame relationships which require meticulous design efforts. Furthermore, when the resulting models are learned on videos, they tend to overfit on the given task distribution and lack in generalization aspect. This begs the following question: How to effectively transfer image-level CLIP representations to videos? In this work, we show that a simple Video Fine-tuned CLIP (ViFi-CLIP) baseline is generally sufficient to bridge the domain gap from images to videos. Our qualitative analysis illustrates that the frame-level processing from CLIP image-encoder followed by feature pooling and similarity matching with corresponding text embeddings helps in implicitly modeling the temporal cues within ViFi-CLIP. Such fine-tuning helps the model to focus on scene dynamics, moving objects and inter-object relationships. For low-data regimes where full fine-tuning is not viable, we propose a `bridge and prompt' approach that first uses fine-tuning to bridge the domain gap and then learns prompts on language and vision side to adapt CLIP representations. We extensively evaluate this simple yet strong baseline on zero-shot, base-to-novel generalization, few-shot and fully supervised settings across five video benchmarks. Our code is available at https://github.com/muzairkhattak/ViFi-CLIP.

Prompt learning is one of the most effective and trending ways to adapt powerful vision-language foundation models like CLIP to downstream datasets by tuning learnable prompt vectors with very few samples. However, although prompt learning achieves excellent performance over in-domain data, it still faces the major challenge of generalizing to unseen classes and domains. Some existing prompt learning methods tackle this issue by adaptively generating different prompts for different tokens or domains but neglecting the ability of learned prompts to generalize to unseen domains. In this paper, we propose a novel prompt learning paradigm that directly generates domain invariant prompt generalizable to unseen domains, called MetaPrompt. Specifically, a dual-modality prompt tuning network is proposed to generate prompts for inputs from both image and text modalities. More importantly, we propose a meta-learning-based prompt tuning algorithm that explicitly constrains the prompt tuned on a specific domain or class also to achieve good performance on another domain or class. Extensive experiments on 11 datasets for base-to-new generalization and four datasets for domain generalization demonstrate that our method consistently and significantly outperforms existing methods.

自动视觉解对我们多样化和开放的世界需要计算机视觉模型，以概括为特定任务的最小定制，类似于人类视力。计算机视觉基础型号培训，培训多样化，大型数据集，可以适应各种下游任务，对该任务来解决现实世界计算机视觉应用而言至关重要。虽然现有的视觉基础模型如剪辑，对齐和吴道2.0主要集中在映射图像和文本表示到跨模型共享表示，我们介绍了一台新的计算机视觉基础模型，佛罗伦萨，扩大粗糙的表示（现场）到精细（对象），从静态（图像）到动态（视频），以及从RGB到多个模态（标题，深度）。通过从Web级图像文本数据中纳入通用视觉语言表示，我们的佛罗伦萨模型可以很容易地适应各种计算机视觉任务，例如分类，检索，对象检测，VQA，图像标题，视频检索和动作识别。此外，佛罗伦萨在许多类型的转移学习中表现出出色的表现：全面采样的微调，线性探测，几次射击传输和用于新颖图像和物体的零拍摄传输。所有这些属性对于我们的视觉基础模型至关重要，以提供通用视觉任务。佛罗伦萨实现了新的最先进的导致44个代表性基准，例如Imagenet-1K零射击分类，最高1精度为83.74，最高5个精度为97.18，62.4地图上的Coco微调， 80.36在VQA上，动力学-600上的87.8。