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。

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。

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。

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.

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。

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.

Joint image-text embedding is the bedrock for most Visionand-Language (V+L) tasks, where multimodality inputs are simultaneously processed for joint visual and textual understanding. In this paper, we introduce UNITER, a UNiversal Image-TExt Representation, learned through large-scale pre-training over four image-text datasets (COCO, Visual Genome, Conceptual Captions, and SBU Captions), which can power heterogeneous downstream V+L tasks with joint multimodal embeddings. We design four pre-training tasks: Masked Language Modeling (MLM), Masked Region Modeling (MRM, with three variants), Image-Text Matching (ITM), and Word-Region Alignment (WRA). Different from previous work that applies joint random masking to both modalities, we use conditional masking on pre-training tasks (i.e., masked language/region modeling is conditioned on full observation of image/text). In addition to ITM for global image-text alignment, we also propose WRA via the use of Optimal Transport (OT) to explicitly encourage finegrained alignment between words and image regions during pre-training. Comprehensive analysis shows that both conditional masking and OTbased WRA contribute to better pre-training. We also conduct a thorough ablation study to find an optimal combination of pre-training tasks. Extensive experiments show that UNITER achieves new state of the art across six V+L tasks (over nine datasets), including Visual Question

Learning fine-grained interplay between vision and language allows to a more accurate understanding for VisionLanguage tasks. However, it remains challenging to extract key image regions according to the texts for semantic alignments. Most existing works are either limited by textagnostic and redundant regions obtained with the frozen detectors, or failing to scale further due to its heavy reliance on scarce grounding (gold) data to pre-train detectors. To solve these problems, we propose Self-Locator Aided Network (SLAN) for cross-modal understanding tasks without any extra gold data. SLAN consists of a region filter and a region adaptor to localize regions of interest conditioned on different texts. By aggregating cross-modal information, the region filter selects key regions and the region adaptor updates their coordinates with text guidance. With detailed region-word alignments, SLAN can be easily generalized to many downstream tasks. It achieves fairly competitive results on five cross-modal understanding tasks (e.g., 85.7% and 69.2% on COCO image-to-text and text-to-image retrieval, surpassing previous SOTA methods). SLAN also demonstrates strong zero-shot and fine-tuned transferability to two localization tasks.

Large-scale pre-training methods of learning cross-modal representations on image-text pairs are becoming popular for vision-language tasks. While existing methods simply concatenate image region features and text features as input to the model to be pre-trained and use selfattention to learn image-text semantic alignments in a brute force manner, in this paper, we propose a new learning method Oscar 1 , which uses object tags detected in images as anchor points to significantly ease the learning of alignments. Our method is motivated by the observation that the salient objects in an image can be accurately detected, and are often mentioned in the paired text. We pre-train an Oscar model on the public corpus of 6.5 million text-image pairs, and fine-tune it on downstream tasks, creating new state-of-the-arts on six well-established vision-language understanding and generation tasks. 2

在本文中，我们提出了一种单一统一的变压器（UFO），其能够处理视觉语言的单峰输入（例如，图像或语言）或多模式输入（例如，图像和问题的串联）（ VL）表示学习。现有方法通常为每个模态和/或特定融合网络设计个人网络，用于多模式任务。为了简化网络架构，我们使用单个变压器网络并在VL预培训期间强制执行多任务学习，其包括图像文本对比丢失，图像文本匹配丢失和基于双向的屏蔽语言建模损耗SEQ2Seq注意面具。相同的变压器网络用作不同预训练任务中的图像编码器，文本编码器或融合网络。经验上，我们观察不同任务之间的冲突，并在视觉问题应答，Coco图像标题（交叉熵优化）和Nocaps（在香料中）实现新的艺术状态。在其他下游任务中，例如，图像文本检索，我们也实现了竞争性能。

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。

近年来，统一的视觉语言框架已经大大提高，其中大多数采用编码器架构将图像文本任务统一为序列到序列的生成。但是，现有的视频语言（VIDL）模型仍需要在每个任务的模型体系结构和培训目标中进行特定于任务的设计。在这项工作中，我们探索了一个统一的VIDL框架薰衣草，其中蒙版语言建模（MLM）用作所有前训练和下游任务的常见接口。这样的统一导致了简化的模型体系结构，在多模式编码器之上，只需要一个轻巧的MLM头，而不是具有更多参数的解码器。令人惊讶的是，实验结果表明，这个统一的框架在14个VIDL基准测试中实现了竞争性能，涵盖了视频问答，文本到视频检索和视频字幕。广泛的分析进一步证明了薰衣草比现有VIDL方法的优势：（i）在多任务列出时仅使用一组参数值支持所有下游任务； （ii）对各种下游任务的几乎没有概括； （iii）在视频问题回答任务上启用零射门评估。代码可从https://github.com/microsoft/lavender获得。

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。

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。

Vision-Language Transformers can be learned without human labels (e.g. class labels, bounding boxes, etc). Existing work, whether explicitly utilizing bounding boxes or patches, assumes that the visual backbone must first be trained on ImageNet class prediction before being integrated into a multimodal linguistic pipeline. We show that this is not necessary and introduce a new model Vision-Language from Captions (VLC) built on top of Masked Auto-Encoders that does not require this supervision. In fact, in a head-to-head comparison between ViLT, the current state-of-the-art patch-based vision-language transformer which is pretrained with supervised object classification, and our model, VLC, we find that our approach 1. outperforms ViLT on standard benchmarks, 2. provides more interpretable and intuitive patch visualizations, and 3. is competitive with many larger models that utilize ROIs trained on annotated bounding-boxes.

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}.

Vision-and语言（VL）预培训已被证明对各种VL下游任务非常有效。虽然最近的工作表明，基于完全变换器的VL模型可以比以前的基于区域特征的方法更有效，但它们在下游任务上的性能通常显着降低。在本文中，我们呈现仪表〜（\ textbf {m} ultimodal \ textbf {e} nd-to-text \ textbf {t} ransform \ textbf {er}），我们通过它系统地调查如何设计和预先列车基于完全变换器的VL模型以端到端的方式。具体而言，我们将模型设计沿多个尺寸分析：视觉编码器（例如，剪辑 - vit，Swin变压器），文本编码器（例如，Roberta，Deberta），多模式融合（例如，合并注意力与共同关注），架构设计（例如，仅编码器与编码器 - 解码器）和预训练目标（例如，屏蔽图像建模）。我们对广泛的VL任务进行全面实验，并提供有关如何在保持快速推理速度的同时培训表演VL变压器的见解。值得注意的是，仪表〜使用仅使用4M图像进行预培训的VQAV2 TEST-STD设置的精度为77.64 \％，超过最先进的区域特征的VINVL模型+1.04 \％，以及优于以前最好的完全变换器的ALBEF模型+1.6 \％。

大规模的视觉预训练在各种下游任务中都表现出了令人印象深刻的进步。现有方法主要是通过图像和文本的全局表示形式的相似性或对图像和文本特征上的高级交叉模式关注来对跨模式对齐进行建模。但是，由于只有全局图像文本对齐信息，因此他们无法明确学习视觉区域和文本短语之间的细粒语义对齐。在本文中，我们介绍了Loupe，这是一种精细的语义一致性视觉语言预训练框架，该框架从新颖的游戏理论互动的角度学习了细粒度的语义对齐。为了有效地计算游戏理论相互作用，我们进一步提出了一种不确定性感知的神经Shapley交互学习模块。实验表明，Loupe在图像文本检索基准测试中实现了最新的。如果没有任何对象级的人类注释和微调，Loupe就可以在对象检测和视觉接地方面实现竞争性能。更重要的是，Loupe从大规模的原始图像文本对学习细粒语义的新方向。

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

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。