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。

对比视觉语言预培训（剪辑）最近淹没了其可转让的视觉表现学习的关注。由大规模的图像文本对进行监督，剪辑能够对准配对的图像和文本，从而在开放词汇场景中进行零拍摄识别。然而，特定应用与通常预先训练的知识之间存在语义差距，这使得匹配子最优在下游任务上。在本文中，我们提出了VT-CLIP通过可视导向文本来增强视觉语言建模。具体而言，我们指导文本功能以自适应地探索图像上的信息区域，并通过跨关注的Machanism聚合视觉特征。以这种方式，视觉引导文本与图像变得更加语义相关，这极大地利益匹配过程。在几次拍摄的设置中，我们在11名知名分类数据集中评估我们的VT-CLIP，并进行实验广泛的消融研究，以证明VT-CLIP的有效性。代码将很快发布。

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。

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.

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.

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.

诸如剪辑之类的对比视觉模型在转移学习方面已显示出巨大进展。在推理阶段，需要仔细设计适当的文本描述，也称为提示，以正确地对给定的图像进行分类。为了避免繁琐的及时工程，最近的作品，例如Coop，Clip-Audapter和Tip-Adapter，建议将视觉模型改编成下游图像识别任务，以在一小部分标记的数据上。尽管实现了有希望的改进，但是需要来自目标数据集的标记数据可能会限制可扩展性。在本文中，我们探讨了一种不同的情况，在该场景中，目标数据集的标签未经证实，并提出了一种无监督的及时学习方法（UPL）方法，以避免及时工程，同时改善类似夹子的视觉模型的传递性能。据我们所知，UPL是第一项将无监督学习引入及时学习的工作。在实验上，我们的UPL在ImageNet以及其他10个数据集上及时使用及时的工程剪辑优于原始剪辑。增强版本的UPL甚至与大多数数据集的8-Shot Coop和8-Shot Tip-Adapter都具有竞争力。代码和型号可在https://github.com/tonyhuang2022/upl上找到。

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.

作为剪辑的对比视觉语言预培训为通过使用大规模对比图像文本对提供了学习视觉表示的新范式。它显示了零击中知识转移到下游任务的令人印象深刻的性能。为了进一步增强剪辑的几次射击功能，提出的剪辑适配器提出微调轻量级残留功能适配器，并显着提高了几次拍摄分类的性能。但是，这样的过程仍然需要额外的培训和计算资源。在本文中，我们提出了\ textbf {t}下雨的cl \ textbf {ip} - \ textbf {适配器}（\ textbf {tip-adapter}），它不仅继承了剪辑的无训练优势，还可以相当地执行或甚至比剪辑适配器更好。提示 - 适配器不需要任何用于训练适配器的备份传播，而是通过从几次拍摄训练集构造的键值高速缓存模型创建权重。在这种非参数的方式中，提示适配器在没有任何训练的情况下获取良好的适配器权重，这既有效且有效。此外，可以通过微调这种适当的初始化适配器进一步提高尖端适配器的性能，仅用于具有超快速收敛速度的几个时期。我们对ImageNet和其他10个数据集进行了广泛的小型分类实验，以证明提出的提示适配器的优越性。代码将以\ URL {https://github.com/gaopengcuhk/tip-adapter}释放。

Pre-trained vision-language models like CLIP have recently shown superior performances on various downstream tasks, including image classification and segmentation. However, in fine-grained image re-identification (ReID), the labels are indexes, lacking concrete text descriptions. Therefore, it remains to be determined how such models could be applied to these tasks. This paper first finds out that simply fine-tuning the visual model initialized by the image encoder in CLIP, has already obtained competitive performances in various ReID tasks. Then we propose a two-stage strategy to facilitate a better visual representation. The key idea is to fully exploit the cross-modal description ability in CLIP through a set of learnable text tokens for each ID and give them to the text encoder to form ambiguous descriptions. In the first training stage, image and text encoders from CLIP keep fixed, and only the text tokens are optimized from scratch by the contrastive loss computed within a batch. In the second stage, the ID-specific text tokens and their encoder become static, providing constraints for fine-tuning the image encoder. With the help of the designed loss in the downstream task, the image encoder is able to represent data as vectors in the feature embedding accurately. The effectiveness of the proposed strategy is validated on several datasets for the person or vehicle ReID tasks. Code is available at https://github.com/Syliz517/CLIP-ReID.

很少有射击分类需要深层神经网络才能仅从有限的培训图像中学习广义表示，这在低数据制度中很有挑战，但很重要。最近，基于剪辑的方法显示出有希望的很少的射击性能受益于对比的语言图像预训练。基于这一点，我们质疑大规模的预训练是否可以减轻少数数据的缺陷，并通过预测的知识帮助代表性学习。在本文中，我们提出了Como，这是对预培训模型的合作，该模型结合了来自各种培训范式的各种先验知识，以获得更好的几次学习。我们的科莫包括：剪辑的语言对比知识，迪诺的视力对抗性知识以及达尔 - E的语言基础知识。具体而言，科莫在两个方面工作：很少的数据扩展和多样化的知识合奏。首先，我们通过零摄影dall-e生成合成图像，以丰富少量训练数据，而无需任何人力。另一方面，我们引入了一个可学习的多知识适配器（MK-apapter），以适应剪辑和恐龙的预测。通过这种合作，COMO可以完全释放不同的预训练方法的潜力，并将其统一以进行几次分类。我们在11个数据集上进行了广泛的实验，以证明我们方法的优势和概括能力。

对比性语言图像预训练（剪辑）已被证明可以学习具有出色传递性的视觉表示，从而实现了零击分类的有希望的准确性。为了进一步提高其下游性能，现有作品在剪辑上提出了其他可学习的模块，并通过几次训练集对其进行微调。但是，由此产生的额外培训成本和数据要求严重阻碍了模型部署和知识转移的效率。在本文中，我们引入了一种自由午餐的增强方法CALIP，以通过无参数注意模块来提高Clip的零拍摄性能。具体而言，我们指导视觉和文本表示相互交互，并通过注意探索跨模式的信息特征。由于预训练大大降低了两种方式之间的嵌入距离，因此我们在注意力中丢弃所有可学习的参数，并在双向更新多模式特征，从而使整个过程无参数且无培训。通过这种方式，图像与文本感知信号混合在一起，文本表示形式被视觉引导以获得更好的自适应零射击对齐。我们在14个数据集的各种基准上评估CALIP，用于2D图像和3D Point Cloud几乎没有分类，显示出一致的零弹性性能改进了夹子。基于此，我们进一步在Calip的注意模块中插入了少量线性层，并在少量射击设置下验证我们的鲁棒性，与现有方法相比，这也可以实现领先的性能。这些广泛的实验证明了我们的方法在有效增强夹子方面的优势。

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。

视觉模型最近在许多计算机视觉任务上显示出巨大的潜力。同时，与线性探针相比，先前的工作表明，与线性探针相比，这是较少的图像识别的迅速调整，可以在很少的图像识别上获得卓越的性能。在实际应用程序中，相关的几个射击任务是相关的，尤其是在专业领域。但是，以前的工作忽略了此类信息。受到以下事实的启发，即通过多任务学习通常可以提高性能，我们提出了一种新颖的方法softcpt（迅速调整的软上下文共享），以微调多个目标几个目标任务的预训练的视觉模型， 同时。具体来说，我们设计了一个任务共享的元网络，以使用预定义的任务名称以及可学习的元提示为输入为每个任务生成提示向量。因此，所有任务的迅速向量将以软的方式共享。该共享的元网络的参数以及元提示向量都在所有目标任务的联合培训集中调整。在三个多任务少量数据集上进行的广泛实验表明，SoftCpt的表现优于代表性的单任务提示方法Coop [78]，这意味着多任务学习在视觉及时及时调整中的有效性。源代码和数据将公开可用。

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。

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。

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.

最近的进展表明，使用对比图像文本对的大规模预训练可以是从自然语言监督的高质量视觉表演学习的有前途的替代方案。从更广泛的监督来源受益，这种新的范例展示了对下游分类任务和数据集的令人印象深刻的可转移性。然而，从图像文本对中学习的知识转移到更复杂的密集预测任务的问题几乎没有访问过。在这项工作中，我们通过隐式和明确地利用来自剪辑的预先训练的知识来提出了一种新的密集预测框架。具体地，我们将剪辑中的原始图像文本匹配问题转换为像素文本匹配问题，并使用像素文本分数图来指导致密预测模型的学习。通过进一步使用图像中的上下文信息来提示语言模型，我们能够促进我们的模型来更好地利用预先接受训练的知识。我们的方法是模型 - 不可行的，它可以应用于任意密集的预测系统和各种预先训练的视觉底座，包括夹模型和想象成预先训练的模型。广泛的实验证明了我们对语义分割，对象检测和实例分段任务的方法的卓越性能。代码可在https://github.com/raoyongming/denseclip获得

Large-scale cross-modal pre-training paradigms have recently shown ubiquitous success on a wide range of downstream tasks, e.g., zero-shot classification, retrieval and image captioning. However, their successes highly rely on the scale and quality of web-crawled data that naturally contain incomplete and noisy information (e.g., wrong or irrelevant content). Existing works either design manual rules to clean data or generate pseudo-targets as auxiliary signals for reducing noise impact, which do not explicitly tackle both the incorrect and incomplete challenges simultaneously. In this paper, to automatically mitigate the impact of noise by solely mining over existing data, we propose a principled Noise-robust Language-Image Pre-training framework (NLIP) to stabilize pre-training via two schemes: noise-harmonization and noise-completion. First, in noise-harmonization scheme, NLIP estimates the noise probability of each pair according to the memorization effect of cross-modal transformers, then adopts noise-adaptive regularization to harmonize the cross-modal alignments with varying degrees. Second, in noise-completion scheme, to enrich the missing object information of text, NLIP injects a concept-conditioned cross-modal decoder to obtain semantic-consistent synthetic captions to complete noisy ones, which uses the retrieved visual concepts (i.e., objects' names) for the corresponding image to guide captioning generation. By collaboratively optimizing noise-harmonization and noise-completion schemes, our NLIP can alleviate the common noise effects during image-text pre-training in a more efficient way. Extensive experiments show the significant performance improvements of our NLIP using only 26M data over existing pre-trained models (e.g., CLIP, FILIP and BLIP) on 12 zero-shot classification datasets, MSCOCO image captioning and zero-shot image-text retrieval tasks.

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.