受益于大规模预处理的视觉语言模型（VL-PMS），视觉问答的性能（VQA）已开始接近人类的甲骨文表现。但是，对VQA数据有限的大规模VL-PM的固定通常面临过度拟合和泛化问题，从而导致缺乏健壮性。在本文中，我们旨在提高VQA系统的鲁棒性（即，当系统对VQA的VL-PMS进行验证时，从信息瓶颈的角度来看，系统能够防御投入变化和人类对抗攻击的能力）。通常，通过VL-PMS获得的内部表示不可避免地包含有关下游VQA任务的无关和冗余信息，从而导致统计上的虚假相关性和对输入变化的不敏感性。为了鼓励表示形式收敛到视觉学习中的足够统计量，我们提出了相关信息瓶颈（CIB）原则，该原则通过最大程度地减少投入和内部表示之间的相互信息（MI）来寻求表示压缩和冗余之间的权衡。同时最大化输出和表示之间的MI。同时，CIB通过对称的关节MI估计来测量视觉和语言输入和表示之间的内部相关性。对五个VQA的投入鲁棒性和两个VQA基准的大量实验证明了拟议CIB在改善VQA系统鲁棒性方面的有效性和优越性。

We present VILLA, the first known effort on large-scale adversarial training for vision-and-language (V+L) representation learning. VILLA consists of two training stages: (i) task-agnostic adversarial pre-training; followed by (ii) task-specific adversarial finetuning. Instead of adding adversarial perturbations on image pixels and textual tokens, we propose to perform adversarial training in the embedding space of each modality. To enable large-scale training, we adopt the "free" adversarial training strategy, and combine it with KL-divergence-based regularization to promote higher invariance in the embedding space. We apply VILLA to current best-performing V+L models, and achieve new state of the art on a wide range of tasks, including Visual Question Answering, Visual Commonsense Reasoning, Image-Text Retrieval, Referring Expression Comprehension, Visual Entailment, and NLVR 2 . 1

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

随着变压器的发展，近年来预先训练的模型已经以突破性的步伐发展。他们在自然语言处理（NLP）和计算机视觉（CV）中主导了主流技术。如何将预训练适应视觉和语言（V-L）学习和改善下游任务绩效成为多模式学习的重点。在本文中，我们回顾了视力语言预训练模型（VL-PTMS）的最新进展。作为核心内容，我们首先简要介绍了几种方法，将原始图像和文本编码为单模式嵌入在预训练之前。然后，我们在建模文本和图像表示之间的相互作用时深入研究VL-PTM的主流体系结构。我们进一步提出了广泛使用的预训练任务，然后我们介绍了一些常见的下游任务。我们终于结束了本文，并提出了一些有前途的研究方向。我们的调查旨在为研究人员提供合成和指向相关研究的指针。

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

自我监督的视觉和语言预处理（VLP）旨在从大规模的图像文本数据中学习可转移的多模式表示形式，并在填充后在广泛的视觉范围内实现强大的表现。以前的主流VLP方法通常采用依靠外部对象检测器来编码多模式变压器框架中的图像的两步策略，该框架遭受了限制性对象概念空间，有限的图像上下文和效率低下的计算。在本文中，我们提出了一个对象感知的端到端VLP框架，该框架将来自CNN的图像网格特征直接馈送到变压器中，并共同学习多模式表示。更重要的是，我们建议执行对象知识蒸馏，以促进在不同语义级别的学习跨模式对齐。为了实现这一目标，我们通过将对象特征及其来自外部检测器的语义标签作为监督来设计两个新颖的借口任务：1。）对象引导的蒙版视觉建模任务的重点是在多模式变压器中强制执行对象感知的表示的学习； 2.）短语区域对准任务旨在通过利用语言空间中名词短语和对象标签之间的相似性来改善跨模式对齐。对各种视觉语言任务进行的广泛实验证明了我们提出的框架的功效，并且我们在现有的预科策略中实现了竞争性或优越的表现。

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.

随着图像文本对的大量数据以及视觉和语言（V＆L）任务的多样性，学者在该研究领域引入了大量的深度学习模型。此外，近年来，转移学习还显示出在计算机愿景中的巨大成功，例如图像分类，对象检测等以及在自然语言处理中以进行问答，机器翻译等的自然语言处理。继承转移学习的精神， V＆L的研究工作已经在大规模数据集上设计了多种预训练技术，以增强下游任务的性能。本文的目的是提供当代V＆L预审前模型的全面修订。特别是，我们对预处理的方法进行了分类和描述，以及最先进的视觉和语言预训练模型的摘要。此外，还提供了培训数据集和下游任务的列表，以进一步提高V＆L预处理的观点。最后，我们决定采取进一步的一步，讨论众多未来研究的方向。

我们启动了对MLP架构进行了视觉和语言（VL）融合的第一个实证研究。通过对5 VL任务和5个强大的VQA基准测试的广泛实验，我们发现：（i）没有预先训练，使用MLP进行多模式融合，与变压器相比具有明显的性能差距; （ii）但是，VL预培训可以帮助关闭性能差距; （iii）代替重大的多主头注意力，将微小的单臂注意MLPS增加足以实现对变压器的可比性。此外，我们还发现，当在更难的鲁棒VQA基准测试时，MLP和变压器之间的性能差距不会扩大，建议使用MLP融合可以大致呈现与使用变压器相似的程度。这些结果提示MLP可以有效地学会对准从较低级别的编码器中提取的视觉和文本功能，而不依赖于自我关注。基于此，我们提出了一个更大胆的问题：我们可以为VL建模提供全部MLP架构，其中VL融合和视觉编码器都用MLPS替换吗？我们的结果表明，与最先进的全功能VL模型相比，全部MLP VL模型是当它们都获得预先培训的时型vl模型。然而，预先培训ALL-MLP可能令人惊讶地实现比没有预先训练的完整变压器模型更好的平均分数。这表明VL建模的MLP样架构的大规模预培训的潜力，并激发了未来的研究方向，简化了较少的归纳设计偏差的良好的VL建模。我们的代码可公开提供：https://github.com/easonnie/mlp-vil

神经网络通常使预测依赖于数据集的虚假相关性，而不是感兴趣的任务的内在特性，面对分布外（OOD）测试数据的急剧下降。现有的De-Bias学习框架尝试通过偏置注释捕获特定的DataSet偏差，它们无法处理复杂的“ood方案”。其他人在低能力偏置模型或损失上隐含地识别数据集偏置，但在训练和测试数据来自相同分布时，它们会降低。在本文中，我们提出了一般的贪婪去偏见学习框架（GGD），它贪婪地训练偏置模型和基础模型，如功能空间中的梯度下降。它鼓励基础模型专注于用偏置模型难以解决的示例，从而仍然在测试阶段中的杂散相关性稳健。 GGD在很大程度上提高了各种任务的模型的泛化能力，但有时会过度估计偏置水平并降低在分配测试。我们进一步重新分析了GGD的集合过程，并将课程正规化为由课程学习启发的GGD，这取得了良好的分配和分发性能之间的权衡。对图像分类的广泛实验，对抗问题应答和视觉问题应答展示了我们方法的有效性。 GGD可以在特定于特定于任务的偏置模型的设置下学习更强大的基础模型，其中具有现有知识和自组合偏置模型而无需先验知识。

We study joint learning of Convolutional Neural Network (CNN) and Transformer for vision-language pre-training (VLPT) which aims to learn cross-modal alignments from millions of image-text pairs. State-of-the-art approaches extract salient image regions and align regions with words step-by-step. As region-based visual features usually represent parts of an image, it is challenging for existing visionlanguage models to fully understand the semantics from paired natural languages. In this paper, we propose SOHO to "See Out of tHe bOx" that takes a whole image as input, and learns vision-language representation in an endto-end manner. SOHO does not require bounding box annotations which enables inference 10 times faster than regionbased approaches. In particular, SOHO learns to extract comprehensive yet compact image features through a visual dictionary (VD) that facilitates cross-modal understanding. VD is designed to represent consistent visual abstractions of similar semantics. It is updated on-the-fly and utilized in our proposed pre-training task Masked Visual Modeling (MVM). We conduct experiments on four well-established vision-language tasks by following standard VLPT settings. In particular, SOHO achieves absolute gains of 2.0% R@1 score on MSCOCO text retrieval 5k test split, 1.5% accuracy on NLVR 2 test-P split, 6.7% accuracy on SNLI-VE test split, respectively.

最近的几项研究指出，现有的视觉问题回答（VQA）模型严重遭受了先前的问题的困扰，这是指捕获问题类型和答案之间的表面统计相关性，而忽略了图像内容。通过创建精致的模型或引入额外的视觉注释，已经致力于加强图像依赖性。但是，这些方法无法充分探索视觉提示如何显式影响学习的答案表示，这对于减轻语言的依赖至关重要。此外，他们通常强调对学习的答案表示形式的班级歧视，这忽略了更精细的实例级别模式，并要求进一步优化。在本文中，我们从视觉扰动校准的角度提出了一种新颖的协作学习方案，该方案可以更好地研究细粒度的视觉效果，并通过学习实例级别的特征来减轻语言的先验问题。具体而言，我们设计了一个视觉控制器来构建具有不同扰动范围的两种策划图像，基于该图像的协作学习内置不变性和实体歧视的协作学习由两个精心设计的歧视者实现。此外，我们在潜在空间上实施信息瓶颈调制器，以进一步减轻偏见和表示校准。我们将视觉扰动感知框架强加于三个正统基准，并将实验结果对两个诊断性VQA-CP基准数据集进行了实验结果，显然表明了其有效性。此外，我们还证明了它在平衡的VQA基准上的鲁棒性是合理的。

大规模预制速度迅速成为视觉语言（VL）建模中的规范。然而，普遍的VL方法受标记数据的要求和复杂的多步预介质目标的要求受限。我们呈现Magma - 使用基于适配器的FineTuning使用额外的方式增强生成语言模型的简单方法。在冻结的情况下，我们培训一系列VL模型，从视觉和文本输入的任意组合自动生成文本。使用单一语言建模目的，预先预测完全结束于结束，与先前的方法相比，简化优化。重要的是，在培训期间，语言模型权重保持不变，允许从语言预磨练转移百科全书知识和内心的学习能力。 Magma在开放式生成任务上冻结的岩浆，实现了最先进的状态，结果在Okvqa基准和竞争结果上的一系列其他流行的VL基准测试中，同时预先训练用于培训SIMVLM的样本数量的0.2％。

基于信息瓶颈（IB）的多视图学习提供了一种信息理论原则，用于寻找异质数据描述中包含的共享信息。但是，它的巨大成功通常归因于估计网络变得复杂时棘手的多元互助信息。此外，表示折衷的表示，{\ it}，预测压缩和足够的一致性权衡，使IB难以同时满足这两个要求。在本文中，我们设计了几种变分信息瓶颈，以利用两个关键特征（{\ it，即}，充分性和一致性）用于多视图表示学习。具体而言，我们提出了一种多视图变量蒸馏（MV $^2 $ d）策略，以通过给出观点的任意输入，但没有明确估算它，从而为拟合MI提供了可扩展，灵活和分析的解决方案。在严格的理论保证下，我们的方法使IB能够掌握观测和语义标签之间的内在相关性，从而自然产生预测性和紧凑的表示。同样，我们的信息理论约束可以通过消除任务 - 求核和特定信息的信息来有效地中和对异质数据的敏感性，从而阻止在多种视图情况下两种权衡。为了验证理论上的策略，我们将方法应用于三种不同应用下的各种基准。广泛的定量和定性实验证明了我们对最新方法的方法的有效性。

Contrastive language-image pretraining (CLIP) links vision and language modalities into a unified embedding space, yielding the tremendous potential for vision-language (VL) tasks. While early concurrent works have begun to study this potential on a subset of tasks, important questions remain: 1) What is the benefit of CLIP on unstudied VL tasks? 2) Does CLIP provide benefit in low-shot or domain-shifted scenarios? 3) Can CLIP improve existing approaches without impacting inference or pretraining complexity? In this work, we seek to answer these questions through two key contributions. First, we introduce an evaluation protocol that includes Visual Commonsense Reasoning (VCR), Visual Entailment (SNLI-VE), and Visual Question Answering (VQA), across a variety of data availability constraints and conditions of domain shift. Second, we propose an approach, named CLIP Targeted Distillation (CLIP-TD), to intelligently distill knowledge from CLIP into existing architectures using a dynamically weighted objective applied to adaptively selected tokens per instance. Experiments demonstrate that our proposed CLIP-TD leads to exceptional gains in the low-shot (up to 51.9%) and domain-shifted (up to 71.3%) conditions of VCR, while simultaneously improving performance under standard fully-supervised conditions (up to 2%), achieving state-of-art performance on VCR compared to other single models that are pretrained with image-text data only. On SNLI-VE, CLIP-TD produces significant gains in low-shot conditions (up to 6.6%) as well as fully supervised (up to 3%). On VQA, CLIP-TD provides improvement in low-shot (up to 9%), and in fully-supervised (up to 1.3%). Finally, CLIP-TD outperforms concurrent works utilizing CLIP for finetuning, as well as baseline naive distillation approaches. Code will be made available.

Vision-and-language reasoning requires an understanding of visual concepts, language semantics, and, most importantly, the alignment and relationships between these two modalities. We thus propose the LXMERT (Learning Cross-Modality Encoder Representations from Transformers) framework to learn these vision-and-language connections. In LXMERT, we build a large-scale Transformer model that consists of three encoders: an object relationship encoder, a language encoder, and a cross-modality encoder. Next, to endow our model with the capability of connecting vision and language semantics, we pre-train the model with large amounts of image-and-sentence pairs, via five diverse representative pre-training tasks: masked language modeling, masked object prediction (feature regression and label classification), cross-modality matching, and image question answering. These tasks help in learning both intra-modality and cross-modality relationships. After fine-tuning from our pretrained parameters, our model achieves the state-of-the-art results on two visual question answering datasets (i.e., VQA and GQA). We also show the generalizability of our pretrained cross-modality model by adapting it to a challenging visual-reasoning task, NLVR 2 , and improve the previous best result by 22% absolute (54% to 76%). Lastly, we demonstrate detailed ablation studies to prove that both our novel model components and pretraining strategies significantly contribute to our strong results; and also present several attention visualizations for the different encoders. 1

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。

This paper focuses on analyzing and improving the commonsense ability of recent popular vision-language (VL) models. Despite the great success, we observe that existing VL-models still lack commonsense knowledge/reasoning ability (e.g., "Lemons are sour"), which is a vital component towards artificial general intelligence. Through our analysis, we find one important reason is that existing large-scale VL datasets do not contain much commonsense knowledge, which motivates us to improve the commonsense of VL-models from the data perspective. Rather than collecting a new VL training dataset, we propose a more scalable strategy, i.e., "Data Augmentation with kNowledge graph linearization for CommonsensE capability" (DANCE). It can be viewed as one type of data augmentation technique, which can inject commonsense knowledge into existing VL datasets on the fly during training. More specifically, we leverage the commonsense knowledge graph (e.g., ConceptNet) and create variants of text description in VL datasets via bidirectional sub-graph sequentialization. For better commonsense evaluation, we further propose the first retrieval-based commonsense diagnostic benchmark. By conducting extensive experiments on some representative VL-models, we demonstrate that our DANCE technique is able to significantly improve the commonsense ability while maintaining the performance on vanilla retrieval tasks. The code and data are available at https://github.com/pleaseconnectwifi/DANCE

Vision-Language预培训是一个新兴和快速发展的研究主题，将多模态知识从丰富的资源预训练任务转移到有限资源下游任务。与主要学习单个通用编码器的现有作品不同，我们提出了一种可训练的通用编码器 - 解码器网络（UNI-EDEN），以促进视觉语言感知（例如，视觉问题应答）和生成（例如，图像标题）。 UNI-EDEN是一种基于双流变换器的结构，由三个模块组成：对象和句子编码器，其单独了解每个模态的表示，以及通过模态交互能够实现多模态推理和句子的句子解码器。考虑到每个图像的语言表示可以跨越该层次结构的不同粒度，包括从简单到全面，个人标签，短语和自然句子，我们通过多粒愿景语言代理任务预先列车UNI-EDEN：屏蔽对象分类（MOC），蒙版区域短语生成（MRPG），图像句匹配（ISM）和屏蔽句生成（MSG）。以这种方式，UNI-EDEN赋予了多模态表示提取和语言建模的功率。广泛的实验证明了通过微调到四个视觉语言感知和发电下游任务来展示Uni-Eden的概括性。

视觉问题应答（VQA）任务利用视觉图像和语言分析来回回答图像的文本问题。它是一个流行的研究课题，在过去十年中越来越多的现实应用。本文介绍了我们最近对AliceMind-MMU的研究（阿里巴巴的编码器 - 解码器来自Damo Academy - 多媒体理解的机器智能实验室），其比人类在VQA上获得相似甚至略微更好的结果。这是通过系统地改善VQA流水线来实现的，包括：（1）具有全面的视觉和文本特征表示的预培训; （2）与学习参加的有效跨模型互动; （3）一个新颖的知识挖掘框架，具有专门的专业专家模块，适用于复杂的VQA任务。处理不同类型的视觉问题，需要具有相应的专业知识在提高我们的VQA架构的表现方面发挥着重要作用，这取决于人力水平。进行了广泛的实验和分析，以证明新的研究工作的有效性。