This paper presents a Generative RegIon-to-Text transformer, GRiT, for object understanding. The spirit of GRiT is to formulate object understanding as <region, text> pairs, where region locates objects and text describes objects. For example, the text in object detection denotes class names while that in dense captioning refers to descriptive sentences. Specifically, GRiT consists of a visual encoder to extract image features, a foreground object extractor to localize objects, and a text decoder to generate open-set object descriptions. With the same model architecture, GRiT can understand objects via not only simple nouns, but also rich descriptive sentences including object attributes or actions. Experimentally, we apply GRiT to object detection and dense captioning tasks. GRiT achieves 60.4 AP on COCO 2017 test-dev for object detection and 15.5 mAP on Visual Genome for dense captioning. Code is available at https://github.com/JialianW/GRiT

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。

使用图像文本对的对比语言图像预测（剪辑）在零拍摄和传输学习设置中的图像分类中取得了令人印象深刻的结果。但是，我们表明，直接应用此类模型以识别对象检测的图像区域导致由于域移位导致的性能差：剪辑训练以与文本描述的整体匹配，而不捕获图像之间的细粒度对齐地区和文本跨度。为了缓解此问题，我们提出了一种称为RegionClip的新方法，可显着扩展剪辑以学习区域级视觉表示，从而在图像区域和文本概念之间实现细粒度对齐。我们的方法利用剪辑模型将图像区域与模板标题匹配，然后预先列出我们的模型以对准要素空间中的这些区域文本对。将预磨料模型转移到开放词汇对象检测任务时，我们的方法显着优于3.8 AP50和2.2 AP的最新技术，分别用于COCO和LVIS数据集的新型类别。更多，学习区域表示支持对象检测的零拍摄推断，显示了对COCO和LVIS数据集的有希望的结果。我们的代码可在https://github.com/microsoft/regionclip上获得。

图像字幕的当前最新方法采用基于区域的特征，因为它们提供了对象级信息，对于描述图像的内容至关重要；它们通常由对象检测器（例如更快的R-CNN）提取。但是，他们有几个问题，例如缺乏上下文信息，不准确检测的风险以及高计算成本。可以通过使用基于网格的功能来解决前两个。但是，如何提取和融合这两种功能是未知的。本文提出了一种仅使用变压器的神经结构，称为砂砾（基于网格和区域的图像字幕变压器），该构建物有效地利用了两个视觉特征来生成更好的字幕。粒度用基于DITR的方法代替了以前方法中使用的基于CNN的检测器，从而使其更快地计算。此外，它的整体设计仅由变压器组成，可以对模型进行端到端的训练。这种创新的设计和双重视觉功能的集成带来了重大的性能提高。几个图像字幕基准的实验结果表明，砂砾的推论准确性和速度优于先前的方法。

标记数据通常昂贵且耗时，特别是对于诸如对象检测和实例分割之类的任务，这需要对图像的密集标签进行密集的标签。虽然几张拍摄对象检测是关于培训小说中的模型（看不见的）对象类具有很少的数据，但它仍然需要在许多标记的基础（见）类的课程上进行训练。另一方面，自我监督的方法旨在从未标记数据学习的学习表示，该数据转移到诸如物体检测的下游任务。结合几次射击和自我监督的物体检测是一个有前途的研究方向。在本调查中，我们审查并表征了几次射击和自我监督对象检测的最新方法。然后，我们给我们的主要外卖，并讨论未来的研究方向。https://gabrielhuang.github.io/fsod-survey/的项目页面

长期以来，将物体检测推向开放量和几乎没有射击转移一直是计算机视觉研究的挑战。这项工作探讨了一种持续的学习方法，该方法使探测器能够通过多数据远见语言的预训练扩展其零/少量功能。我们使用自然语言作为知识表示，我们探讨了从不同培训数据集积累“视觉词汇”的方法，并将任务统一为语言条件的检测框架。具体而言，我们提出了一种新颖的语言感知探测器OMDET和一种新颖的培训机制。拟议的多模式检测网络可以解决多数据库联合培训中的技术挑战，并且可以推广到任意数量的培训数据集，而无需手动标签分类合并的要求。与单独训练相比，Coco，Pascal VOC和更宽的面部/行人的实验结果通过在关节训练中或更高的分数来证实了疗效。此外，我们对超过400万个独特的对象词汇进行了预先培训，并在ODINW的35个下游任务上评估了所得模型。结果表明，OMDET能够在ODINW上实现最新的微调性能。分析表明，通过扩展提出的预训练方法，OMDET继续改善其零/少量调整性能，这表明了进一步扩展的有希望的方法。

构建强大的通用对象检测框架需要扩展到更大的标签空间和更大的培训数据集。但是，大规模获取数千个类别的注释是高昂的成本。我们提出了一种新颖的方法，该方法利用了最近的视觉和语言模型中可用的丰富语义来将对象定位和分类在未标记的图像中，从而有效地生成了伪标签以进行对象检测。从通用和类别的区域建议机制开始，我们使用视觉和语言模型将图像的每个区域分类为下游任务所需的任何对象类别。我们在两个特定的任务（开放式摄影检测检测）中演示了生成的伪标签的值，其中模型需要概括为看不见的对象类别以及半监督对象检测，其中可以使用其他未标记的图像来改善模型。我们的经验评估显示了伪标签在这两个任务中的有效性，我们在其中优于竞争基准并实现了开放式摄制对象检测的新颖最新。我们的代码可在https://github.com/xiaofeng94/vl-plm上找到。

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。

尽管对象检测方面取得了很大进展，但由于实例级边界盒注释所需的巨大人性化，大多数现有方法都仅限于一小一少量的对象类别。为了减轻问题，最近的开放词汇和零射击检测方法试图检测培训期间未见的对象类别。但是，这些方法仍然依赖于一组基类上手动提供的边界盒注释。我们提出了一个开放的词汇检测框架，可以在没有手动提供边界盒注释的情况下培训。我们的方法通过利用预先训练的视觉语言模型的本地化能力来实现这一目标，并产生可直接用于训练对象探测器的伪边界盒标签。 Coco，Pascal VOC，Objects365和LVIS的实验结果证明了我们方法的有效性。具体而言，我们的方法优于使用人类注释的边界箱训练的最先进（SOTA），即使我们的培训源未配备手动边界盒标签，也可以在COCO新型类别上用3％AP培训。在利用手动边界箱标签作为基线时，我们的方法主要超过8％的AP。

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.

在这项工作中，我们提出了一种开放式摄制对象检测方法，该方法基于图像映射对，学会了检测新颖对象类别以及给定的一组已知类别。这是一种两阶段的训练方法，首先使用位置引导的图像捕获匹配技术以弱监督的方式学习新颖和已知类别的类标签，第二个使用已知的类注释专用于对象检测任务的模型。我们表明，一个简单的语言模型比检测新对象的大型上下文化语言模型更适合。此外，我们引入了一种一致性调查技术，以更好地利用图像捕获对信息。我们的方法比较与现有的开放式检测方法相比，同时具有数据效率。源代码可从https://github.com/lmb-freiburg/locov获得。

Modern object detectors have taken the advantages of backbone networks pre-trained on large scale datasets. Except for the backbone networks, however, other components such as the detector head and the feature pyramid network (FPN) remain trained from scratch, which hinders fully tapping the potential of representation models. In this study, we propose to integrally migrate pre-trained transformer encoder-decoders (imTED) to a detector, constructing a feature extraction path which is ``fully pre-trained" so that detectors' generalization capacity is maximized. The essential differences between imTED with the baseline detector are twofold: (1) migrating the pre-trained transformer decoder to the detector head while removing the randomly initialized FPN from the feature extraction path; and (2) defining a multi-scale feature modulator (MFM) to enhance scale adaptability. Such designs not only reduce randomly initialized parameters significantly but also unify detector training with representation learning intendedly. Experiments on the MS COCO object detection dataset show that imTED consistently outperforms its counterparts by $\sim$2.4 AP. Without bells and whistles, imTED improves the state-of-the-art of few-shot object detection by up to 7.6 AP. Code is available at https://github.com/LiewFeng/imTED.

Despite the superior performance brought by vision-and-language pretraining, it remains unclear whether learning with multi-modal data can help understand each individual modality. In this work, we investigate how language can help with visual representation learning from a probing perspective. Specifically, we compare vision-and-language and vision-only models by probing their visual representations on a broad range of tasks, in order to assess the quality of the learned representations in a fine-grained manner. Interestingly, our probing results suggest that vision-and-language models are better at label prediction tasks like object and attribute prediction, while vision-only models are stronger at dense prediction tasks that require more localized information. With further analysis using detailed metrics, our study suggests that language helps vision models learn better semantics, but not localization. Code is released at https://github.com/Lizw14/visual_probing.

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。

Existing object detection methods are bounded in a fixed-set vocabulary by costly labeled data. When dealing with novel categories, the model has to be retrained with more bounding box annotations. Natural language supervision is an attractive alternative for its annotation-free attributes and broader object concepts. However, learning open-vocabulary object detection from language is challenging since image-text pairs do not contain fine-grained object-language alignments. Previous solutions rely on either expensive grounding annotations or distilling classification-oriented vision models. In this paper, we propose a novel open-vocabulary object detection framework directly learning from image-text pair data. We formulate object-language alignment as a set matching problem between a set of image region features and a set of word embeddings. It enables us to train an open-vocabulary object detector on image-text pairs in a much simple and effective way. Extensive experiments on two benchmark datasets, COCO and LVIS, demonstrate our superior performance over the competing approaches on novel categories, e.g. achieving 32.0% mAP on COCO and 21.7% mask mAP on LVIS. Code is available at: https://github.com/clin1223/VLDet.

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。

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}.

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.

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。

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.