通用视觉（GPV）系统是旨在解决各种视觉任务的模型，而无需进行架构更改。如今，GPV主要从大型完全监督的数据集中学习技能和概念。通过获取数据以迅速学习每个技能的每个概念，将GPV扩展到数万个概念都变得令人望而却步。这项工作提出了一种有效且廉价的替代方法：从监督数据集中学习技能，从Web图像搜索中学习概念，并利用GPV的关键特征：跨技能传递视觉知识的能力。我们使用跨越10K+视觉概念的1M+图像的数据集来演示3个基准上的两个现有GPV（GPV-1和VL-T5）的Webly Supumented概念扩展：5个基于可可的数据集（80个主要概念），这是一个新的策划系列，这是一个新的策划系列。基于OpenImages和VisualGenome存储库（〜500个概念）以及Web衍生的数据集（10K+概念）的5个数据集。我们还提出了一种新的体系结构GPV-2，该架构支持各种任务 - 从分类和本地化等视觉任务到Qu Viewer+语言任务，例如QA和字幕，再到更多的利基市场，例如人类对象互动检测。 GPV-2从Web数据中受益匪浅，并且在这些基准测试中胜过GPV-1和VL-T5。我们的数据，代码和Web演示可在https://prior.allenai.org/projects/gpv2上获得。

我们提出了Unified-io，该模型执行了跨越经典计算机视觉任务的各种AI任务，包括姿势估计，对象检测，深度估计和图像生成，视觉和语言任务，例如区域字幕和引用表达理解，并引用表达理解，进行自然语言处理任务，例如回答和释义。由于与每个任务有关的异质输入和输出，包括RGB图像，每个像素映射，二进制掩码，边界框和语言，开发一个统一模型引起了独特的挑战。我们通过将每个受支持的输入和输出均匀地均匀地统一到一系列离散的词汇令牌来实现这一统一。在所有任务中，这种共同的表示使我们能够在视觉和语言字段中的80多个不同数据集上培训单个基于变压器的体系结构。 Unified-io是第一个能够在砂砾基准上执行所有7个任务的模型，并在NYUV2-DEPTH，Imagenet，VQA2.0，OK-VQA，SWIG，SWIG，VIZWIZ，BOOLQ，BOOLQ和SCITAIL，带有NYUV2-DEPTH，Imagenet，VQA2.0，诸如NYUV2-DEPTH，ImageNet，vqa2.0等16个不同的基准中产生强大的结果。没有任务或基准特定的微调。 unified-io的演示可在https://unified-io.allenai.org上获得。

我们提出了GLIPV2，这是一个接地的VL理解模型，该模型既服务于本地化任务（例如，对象检测，实例分割）和视觉语言（VL）理解任务（例如VQA，图像字幕）。 GLIPV2优雅地将本地化预训练和视觉语言预训练（VLP）具有三个预训练任务：短语接地作为对检测任务的VL重新重新制定，区域词对比度学习作为新型的区域词对比度对比度对比学习任务，以及蒙面的语言建模。这种统一不仅简化了先前的多阶段VLP程序，而且还可以在本地化和理解任务之间实现相互利益。实验结果表明，在各种本地化和理解任务上，单个GLIPV2模型（所有模型权重）在SOTA性能附近实现。该模型还显示了（1）在开放式摄制对象检测任务上进行的强零射击和很少的自适应性能，以及（2）VL理解任务上的卓越接地能力。代码将在https://github.com/microsoft/glip上发布。

在本文中，我们提出了Unicorn，一种vision-language（vl）模型，使文本生成和边界框预测到单个架构中。具体而言，我们将每个框量化为四个离散框令牌，并将其序列化为序列，可以与文本令牌集成。我们将所有VL问题作为一代任务，其中目标序列由集成文本和框令牌组成。然后，我们训练变压器编码器解码器以以自动回归方式预测目标。通过如此统一的框架和输入输出格式，Unicorn在7 VL基准测试中实现了对现有技术的可比性的性能，涵盖了视觉接地，接地字幕，视觉问题应答和图像标题任务。当用多任务FINETUNING培训时，UNICORN可以通过单一的参数方法接近不同的VL任务，从而跨越下游任务边界。我们展示了具有单一模型不仅可以节省参数，而且还可以在某些任务上提高模型性能。最后，Unicorn显示了概括到诸如ImageNet对象本地化的新任务的能力。

This paper presents a detailed study of improving visual representations for vision language (VL) tasks and develops an improved object detection model to provide object-centric representations of images. Compared to the most widely used bottom-up and top-down model [2], the new model is bigger, better-designed for VL tasks, and pre-trained on much larger training corpora that combine multiple public annotated object detection datasets. Therefore, it can generate representations of a richer collection of visual objects and concepts. While previous VL research focuses mainly on improving the vision-language fusion model and leaves the object detection model improvement untouched, we show that visual features matter significantly in VL models. In our experiments we feed the visual features generated by the new object detection model into a Transformer-based VL fusion model OSCAR [21], and utilize an improved approach OSCAR+ to pre-train the VL model and fine-tune it on a wide range of downstream VL tasks. Our results show that the new visual features significantly improve the performance across all VL tasks, creating new state-of-the-art results on seven public benchmarks. Code, models and pre-extracted features are released at https://github.com/pzzhang/VinVL. ♥ Microsoft Corporation♠ University of Washington † indicates equal contributions.

The availability of large-scale image captioning and visual question answering datasets has contributed significantly to recent successes in vision-and-language pretraining. However, these datasets are often collected with overrestrictive requirements inherited from their original target tasks (e.g., image caption generation), which limit the resulting dataset scale and diversity. We take a step further in pushing the limits of vision-and-language pretraining data by relaxing the data collection pipeline used in Conceptual Captions 3M (CC3M) [70] and introduce the Conceptual 12M (CC12M), a dataset with 12 million image-text pairs specifically meant to be used for visionand-language pre-training. We perform an analysis of this dataset and benchmark its effectiveness against CC3M on multiple downstream tasks with an emphasis on long-tail visual recognition. Our results clearly illustrate the benefit of scaling up pre-training data for vision-and-language tasks, as indicated by the new state-of-the-art results on both the nocaps and Conceptual Captions benchmarks. 1

Despite progress in perceptual tasks such as image classification, computers still perform poorly on cognitive tasks such as image description and question answering. Cognition is core to tasks that involve not just recognizing, but reasoning about our visual world. However, models used to tackle the rich content in images for cognitive tasks are still being trained using the same datasets designed for perceptual tasks. To achieve success at cognitive tasks, models need to understand the interactions and relationships between objects in

We present X-Decoder, a generalized decoding model that can predict pixel-level segmentation and language tokens seamlessly. X-Decodert takes as input two types of queries: (i) generic non-semantic queries and (ii) semantic queries induced from text inputs, to decode different pixel-level and token-level outputs in the same semantic space. With such a novel design, X-Decoder is the first work that provides a unified way to support all types of image segmentation and a variety of vision-language (VL) tasks. Further, our design enables seamless interactions across tasks at different granularities and brings mutual benefits by learning a common and rich pixel-level visual-semantic understanding space, without any pseudo-labeling. After pretraining on a mixed set of a limited amount of segmentation data and millions of image-text pairs, X-Decoder exhibits strong transferability to a wide range of downstream tasks in both zero-shot and finetuning settings. Notably, it achieves (1) state-of-the-art results on open-vocabulary segmentation and referring segmentation on eight datasets; (2) better or competitive finetuned performance to other generalist and specialist models on segmentation and VL tasks; and (3) flexibility for efficient finetuning and novel task composition (e.g., referring captioning and image editing). Code, demo, video, and visualization are available at https://x-decoder-vl.github.io.

本文介绍了用于学习对象级别，语言感知和富含语义的视觉表示的接地语言图像预培训（GLIP）模型。 Glip统一对象检测和短语进行预培训。统一带来了两个好处：1）它允许GLIP从检测和接地数据中学习，以改善两个任务和引导良好的接地模型; 2）GLIP可以通过以自培训方式产生接地盒来利用大规模的图像文本对，使学习的表示是语义丰富的。在我们的实验中，我们在27M的接地数据上预先列车触胶，包括3M人的注释和24M Web爬网的图像文本对。学习的表示表明了强烈的零射击和对各种对象识别任务的可转换性。 1）直接在Coco和LVIS上评估（在训练期间没有在Coco中看到任何图像）时，Plip分别达到49.8 AP和26.9 AP，超过许多监督基线。 2）在COCO上微调后，GLIP在Val和61.5 AP上实现60.8 AP在测试开发上，超过先前的SOTA。 3）当转移到下游对象检测任务时，具有完全监控动态头的1次触发器竞争对手。代码将在https://github.com/microsoft/glip发布。

We present Answer-Me, a task-aware multi-task framework which unifies a variety of question answering tasks, such as, visual question answering, visual entailment, visual reasoning. In contrast to previous works using contrastive or generative captioning training, we propose a novel and simple recipe to pre-train a vision-language joint model, which is multi-task as well. The pre-training uses only noisy image captioning data, and is formulated to use the entire architecture end-to-end with both a strong language encoder and decoder. Our results show state-of-the-art performance, zero-shot generalization, robustness to forgetting, and competitive single-task results across a variety of question answering tasks. Our multi-task mixture training learns from tasks of various question intents and thus generalizes better, including on zero-shot vision-language tasks. We conduct experiments in the challenging multi-task and open-vocabulary settings and across a variety of datasets and tasks, such as VQA2.0, SNLI-VE, NLVR2, GQA. We observe that the proposed approach is able to generalize to unseen tasks and that more diverse mixtures lead to higher accuracy in both known and novel tasks.

将简单的体系结构与大规模预训练相结合已导致图像分类的大量改进。对于对象检测，预训练和缩放方法的确定性不佳，尤其是在长尾和开放式摄影的环境中，训练数据相对较少。在本文中，我们提出了一个强大的配方，用于将图像文本模型转移到开放式对象检测中。我们使用具有最小修改，对比度文本预训练和端到端检测微调的标准视觉变压器体系结构。我们对该设置的缩放属性的分析表明，增加图像级预训练和模型大小在下游检测任务上产生一致的改进。我们提供适应性策略和正规化，以实现零击文本条件和单次图像条件对象检测的非常强劲的性能。代码和型号可在GitHub上找到。

我们提出了Findit，这是一个简单而多功能的框架，统一了各种视觉接地和本地化任务，包括引用表达理解，基于文本的本地化和对象检测。我们体系结构的关键是一个有效的多尺度融合模块，该模块统一了整个任务中不同的本地化要求。此外，我们发现标准对象检测器在统一这些任务的无需特定任务设计，损失或预计算检测方面非常有效。我们的端到端可训练框架灵活，准确地响应了零，一个或多个对象的广泛的参考表达，本地化或检测查询。在这些任务上进行了共同培训，发现在引用表达和基于文本的本地化方面，胜过最高的艺术状态，并在对象检测中表现出竞争性的性能。最后，与强大的单任务基准相比，Findit可以更好地推广到分布数据和新型类别。所有这些都是通过一个单一的，统一和有效的模型来完成的。代码将发布。

视觉语言（VL）预训练最近受到了广泛的关注。但是，大多数现有的端到端预训练方法只旨在解决诸如图像文本检索，视觉询问答案（VQA）和图像字幕等VL任务，以测试对图像的高级了解，或者仅对目标区域进行测试 - 对诸如短语接地和对象检测等任务的水平理解。我们提出了Fiber（基于回避的变压器），这是一种新的VL模型体系结构，可以无缝处理这两种类型的任务。 Fiber没有将多模式融合到模型深处，而不是将融合后的专用变压器层用于融合，而是通过将交叉注意力插入图像和文本骨干杆中，从而在记忆和性能方面带来了增长。此外，与以前的工作不同，它要么仅在图像文本数据上进行训练，要么在带有框级注释的细粒度数据上进行培训，我们提出了一种两阶段的预训练策略，该策略有效地使用了这两种数据：（（ i）基于图像文本数据的粗粒细化预训练；然后是（ii）基于图像文本框数据的细粒度预训练。我们对各种VL任务进行全面的实验，从VQA，图像字幕和检索到短语接地，参考表达理解和对象检测。使用深层多模式融合，结合两阶段的预训练，光纤可对所有任务的强基础进行一致的性能改进，通常使用幅度更优于更多数据的方法。代码可从https://github.com/microsoft/fiber获得。

开放世界对象检测是一个更具笼统和挑战性的目标，旨在识别和本地化由任意类别名称描述的对象。最近的工作GLIP通过将检测数据集的所有类别名称连接到句子中，从而将此问题作为接地问题，从而导致类别名称之间的效率低下的相互作用。本文介绍了Distclip，这是一种通过诉诸于设计概念词典的知识富集，是一种平行的视觉概念训练预训练方法，用于开放世界检测。为了提高学习效率，我们提出了一种新型的并行概念公式，该公式分别提取概念，以更好地利用异质数据集（即检测，接地和图像文本对）进行培训。我们进一步设计了来自各种在线资源和检测数据集的概念字典〜（带有描述），以提供每个概念的先验知识。通过用描述丰富这些概念，我们明确地建立了各种概念之间的关系，以促进开放域学习。所提出的概念词典进一步用于提供足够的负面概念，用于构建单词区域对齐损失\，并完成图像对文本对数据标题中缺少描述的对象的标签。所提出的框架显示出强烈的零射击性能性能，例如，在LVIS数据集上，我们的DETCLIP-T优于9.9％的地图GLIPT-T优于GLIP-T，并且与完全避免的型号相比，稀有类别的稀有类别提高了13.5％。作为我们的。

有效的缩放和灵活的任务接口使大型语言模型能够在许多任务中表现出色。帕利（Pali）根据视觉和文本输入生成文本，并使用该界面以许多语言执行许多视觉，语言和多模式任务。为了训练帕利，我们利用了大型的编码器语言模型和视觉变压器（VITS）。这使我们能够利用其现有能力，并利用培训它们的大量成本。我们发现，视觉和语言组成部分的联合缩放很重要。由于现有的语言变压器比其视觉对应物要大得多，因此我们训练迄今为止最大的VIT（VIT-E），以量化甚至大容量视觉模型的好处。为了训练Pali，我们基于一个新的图像文本训练集，其中包含10B图像和文本，以100多种语言来创建大型的多语言组合。帕利（Pali）在多个视觉和语言任务（例如字幕，视觉问题，索方式，场景文本理解）中实现了最新的，同时保留了简单，模块化和可扩展的设计。

We present ViLBERT (short for Vision-and-Language BERT), a model for learning task-agnostic joint representations of image content and natural language. We extend the popular BERT architecture to a multi-modal two-stream model, processing both visual and textual inputs in separate streams that interact through co-attentional transformer layers. We pretrain our model through two proxy tasks on the large, automatically collected Conceptual Captions dataset and then transfer it to multiple established vision-and-language tasks -visual question answering, visual commonsense reasoning, referring expressions, and caption-based image retrieval -by making only minor additions to the base architecture. We observe significant improvements across tasks compared to existing task-specific modelsachieving state-of-the-art on all four tasks. Our work represents a shift away from learning groundings between vision and language only as part of task training and towards treating visual grounding as a pretrainable and transferable capability.Preprint. Under review.

Natural language explanations promise to offer intuitively understandable explanations of a neural network's decision process in complex vision-language tasks, as pursued in recent VL-NLE models. While current models offer impressive performance on task accuracy and explanation plausibility, they suffer from a range of issues: Some models feature a modular design where the explanation generation module is poorly integrated with a separate module for task-answer prediction, employ backbone models trained on limited sets of tasks, or incorporate ad hoc solutions to increase performance on single datasets. We propose to evade these limitations by applying recent advances in large-scale multi-task pretraining of generative Transformer models to the problem of VL-NLE tasks. Our approach outperforms recent models by a large margin, with human annotators preferring the generated explanations over the ground truth in two out of three evaluated datasets. As a novel challenge in VL-NLE research, we propose the problem of multi-task VL-NLE and show that jointly training on multiple tasks can increase the explanation quality. We discuss the ethical implications of high-quality NLE generation and other issues in recent VL-NLE research.

Vision-Language Pre-Training (VLP) has shown promising capabilities to align image and text pairs, facilitating a broad variety of cross-modal learning tasks. However, we observe that VLP models often lack the visual grounding/localization capability which is critical for many downstream tasks such as visual reasoning. In this work, we propose a novel Position-guided Text Prompt (PTP) paradigm to enhance the visual grounding ability of cross-modal models trained with VLP. Specifically, in the VLP phase, PTP divides the image into $N\times N$ blocks, and identifies the objects in each block through the widely used object detector in VLP. It then reformulates the visual grounding task into a fill-in-the-blank problem given a PTP by encouraging the model to predict the objects in the given blocks or regress the blocks of a given object, e.g. filling `P" or ``O" in aPTP ``The block P has a O". This mechanism improves the visual grounding capability of VLP models and thus helps them better handle various downstream tasks. By introducing PTP into several state-of-the-art VLP frameworks, we observe consistently significant improvements across representative cross-modal learning model architectures and several benchmarks, e.g. zero-shot Flickr30K Retrieval (+4.8 in average recall@1) for ViLT \cite{vilt} baseline, and COCO Captioning (+5.3 in CIDEr) for SOTA BLIP \cite{blip} baseline. Moreover, PTP achieves comparable results with object-detector based methods, and much faster inference speed since PTP discards its object detector for inference while the later cannot. Our code and pre-trained weight will be released at \url{https://github.com/sail-sg/ptp}.

Many high-level skills that are required for computer vision tasks, such as parsing questions, comparing and contrasting semantics, and writing descriptions, are also required in other domains such as natural language processing. In this paper, we ask whether this makes it possible to learn those skills from text data and then use them to complete vision tasks without ever training on visual training data. Key to our approach is exploiting the joint embedding space of contrastively trained vision and language encoders. In practice, there can be systematic differences between embedding spaces for different modalities in contrastive models, and we analyze how these differences affect our approach and study a variety of strategies to mitigate this concern. We produce models using only text training data on three tasks: image captioning, visual entailment and visual question answering, and evaluate them on standard benchmarks using images. We find that this kind of transfer is possible and results in only a small drop in performance relative to models trained on images. We also showcase a variety of stylistic image captioning models that were trained using no image data and no human-curated language data, but instead text data from books, the web, or language models.

在本文中，我们设计和训练生成的图像到文本变压器Git，以统一视觉语言任务，例如图像/视频字幕和问题答案。尽管生成模型在预训练和微调之间提供了一致的网络体系结构，但现有工作通常包含复杂的结构（Uni/多模式编码器/解码器），并取决于外部模块，例如对象检测器/标记器和光学角色识别（OCR） ）。在git中，我们将体系结构简化为一个图像编码器，而在单语言建模任务下将架构简化为一个文本解码器。我们还扩展了预训练数据和模型大小，以提高模型性能。没有铃铛和哨子，我们的git在12个具有挑战性的基准下建立了新的艺术状态。例如，我们的模型在文本贴图上首次超过了人类的表现（138.2 vs. 125.5在苹果酒中）。此外，我们提出了一种新的基于一代的图像分类和场景文本识别的方案，在标准基准上实现了不错的表现。