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.
translated by 谷歌翻译
从预训练的语言模型中进行的引导已被证明是用于建立基础视觉模型(VLM)的有效方法,例如图像字幕或视觉问题的答案。但是,很难用它来使模型符合用户的理由来获得特定答案。为了引起和加强常识性原因,我们提出了一个迭代采样和调整范式,称为Illume,执行以下循环:给定图像问题提示提示,VLM采样了多个候选人,并通过人类评论家通过偏好提供最小的反馈。选择,用于微调。该循环增加了训练数据,并逐渐雕刻出VLM的合理化功能。我们的详尽实验表明,Illume在使用较少的培训数据的同时,仅需要最少的反馈,与标准监督的微调竞争。
translated by 谷歌翻译
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。
translated by 谷歌翻译
基础模型由于在广泛的下游应用中的有效性而受到了很多关注。尽管在体系结构方面存在很大的融合,但大多数审慎的模型通常仍用于特定任务或模式。在这项工作中,我们建议将语言模型用作各种基础模型的通用接口。一系列预处理的编码者感知到了多种方式(例如视觉和语言),并与扮演通用任务层角色的语言模型对接。我们提出了一个半伴侣的语言建模目标,以共同确定界面和模块化编码器。我们从因果关系和非因果建模中涵盖了优势和能力,从而结合了两个世界的最佳状态。具体而言,所提出的方法不仅从因果语言建模中继承了内在学习和开放式生成的能力,而且由于双向编码器而有利于填补。更重要的是,我们的方法无缝地解锁了上述功能的组合,例如,通过填充编码器启用了文本学习或指导。各种仅语言和视觉语言基准的实验结果表明,我们的模型表现优于或与鉴定,零弹性概括和几乎没有的学习的专业模型竞争。
translated by 谷歌翻译
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.
translated by 谷歌翻译
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。
translated by 谷歌翻译
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。
translated by 谷歌翻译
This paper presents a unified Vision-Language Pre-training (VLP) model. The model is unified in that (1) it can be finetuned for either vision-language generation (e.g., image captioning) or understanding (e.g., visual question answering) tasks, and (2) it uses a shared multi-layer transformer network for both encoding and decoding, which differs from many existing methods where the encoder and decoder are implemented using separate models. The unified VLP model is pre-trained on a large amount of image-text pairs using the unsupervised learning objectives of two tasks: bidirectional and sequence-to-sequence (seq2seq) masked vision-language prediction. The two tasks differ solely in what context the prediction conditions on. This is controlled by utilizing specific self-attention masks for the shared transformer network. To the best of our knowledge, VLP is the first reported model that achieves state-of-the-art results on both vision-language generation and understanding tasks, as disparate as image captioning and visual question answering, across three challenging benchmark datasets: COCO Captions, Flickr30k Captions, and VQA 2.0. The code and the pre-trained models are available at https://github.com/LuoweiZhou/VLP.
translated by 谷歌翻译
人们说:“一张照片值一千字”。那么,我们如何从图像中获取丰富的信息?我们认为,通过使用视觉线索来桥接大型的识别视觉基础模型和语言模型,我们可以无需任何额外的跨模式训练。得益于基础模型的强大零拍功能,我们首先构建图像的丰富语义表示(例如,图像标签,对象属性 /位置,字幕)作为结构化的文本提示,称为视觉线索,使用视觉基础模型。基于视觉线索,我们使用大型语言模型为视觉内容生成一系列综合描述,然后再次通过视觉模型验证,以选择与图像最合适的候选人。我们通过定量和定性测量评估生成的描述的质量。结果证明了这种结构化语义表示的有效性。
translated by 谷歌翻译
Large language models (LLMs) have demonstrated excellent zero-shot generalization to new language tasks. However, effective utilization of LLMs for zero-shot visual question-answering (VQA) remains challenging, primarily due to the modality disconnection and task disconnection between LLM and VQA task. End-to-end training on vision and language data may bridge the disconnections, but is inflexible and computationally expensive. To address this issue, we propose \emph{Img2Prompt}, a plug-and-play module that provides the prompts that can bridge the aforementioned modality and task disconnections, so that LLMs can perform zero-shot VQA tasks without end-to-end training. In order to provide such prompts, we further employ LLM-agnostic models to provide prompts that can describe image content and self-constructed question-answer pairs, which can effectively guide LLM to perform zero-shot VQA tasks. Img2Prompt offers the following benefits: 1) It can flexibly work with various LLMs to perform VQA. 2)~Without the needing of end-to-end training, it significantly reduces the cost of deploying LLM for zero-shot VQA tasks. 3) It achieves comparable or better performance than methods relying on end-to-end training. For example, we outperform Flamingo~\cite{Deepmind:Flamingo2022} by 5.6\% on VQAv2. On the challenging A-OKVQA dataset, our method even outperforms few-shot methods by as much as 20\%.
translated by 谷歌翻译
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。
translated by 谷歌翻译
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.
translated by 谷歌翻译
预测任务标签和为其预测生成自由文本阐述的自律化模型可以实现与NLP系统更直观的交互。然而,这些模型目前正在接受大量人为的自由文本解释,每个任务都会阻碍更广泛的使用。我们建议使用少数培训例子研究更现实的自律化建立。我们出示2月 - 一个标准化的四个现有英语数据集和相关指标。我们通过2月份广泛探索自然语言提示来确定正确的提示方法。然后,通过使用此提示并缩放模型大小,我们证明了几次拍摄自合合理化的进展。我们展示了这项任务的完善房间仍然有充足的改进空间:人类注册人评估的生成解释的平均合理性最多为51%,而人类解释的合理性是76%。我们希望2月份与我们的拟议方法一起促使社区承担几次拍摄的自我合理化挑战。
translated by 谷歌翻译
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%。
translated by 谷歌翻译
我们挑战AI模型,以“展示”对《纽约客》标题比赛的复杂多模式幽默的理解。具体而言,我们开发了三个精心限制的任务,以掌握图像和标题之间的潜在复杂和意外的关系,并且对人类经验的广泛品种产生了复杂和意外的寓意;这些是纽约口径卡通的标志。我们调查了直接将卡通像素和字幕输入的视觉和语言模型,以及仅通过提供图像的文本描述来规避图像处理的仅限语言模型。即使我们为卡通图像提供了丰富的多方面注释,我们也可以确定高质量的机器学习模型(例如,微调,175b参数语言模型)和人类之间的性能差距。我们公开发布我们的语料库,包括描述图像的位置/实体的注释,场景的不寻常以及对笑话的解释。
translated by 谷歌翻译
支持II社区的当前趋势,我们提出了一个称为融合大脑的AI Journey 2021挑战,这些挑战是融合大脑,该挑战是使普通架构处理不同的方式(即图像,文本和代码),并解决视觉和语言的多个任务。融合脑挑战https://github.com/sberbank- ai/fusion_brain_aij2021结合了以下特定任务:code2code翻译,手写文本识别,零拍摄对象检测和视觉问题应答。我们为每个任务创建了数据集以测试参与者的提交。此外,我们在俄语和英语中开设了一个新的手写数据集,其中包含94,130对图像和文本。DataSet的俄罗斯部分是世界上最大的俄罗斯手写数据集。我们还提出了基线解决方案和相应的特定于任务特定解决方案以及整体指标。
translated by 谷歌翻译
最近,在大型文本语料库上预先培训的微调语言模型已经为Vision-and Langual(V&L)任务以及纯语言任务提供了巨大的改进。但是,微调预训练模型的整个参数集变得不切实际,因为模型大小正在快速增长。因此,在本文中,我们将基于适配器的参数高效转移学习技术引入VL-BART和VL-T5等V&L型号。我们在四个不同V&L任务的统一多任务设置中评估我们的方法:VQAV2,GQA,NLVR2和MSCOCO图像标题。通过仔细的培训和彻底的实验,我们将三种流行的基于适配器的方法(适配器,Hyperformer,Compacter)基准,抵御标准的全部微调和最近提出的及时调整方法。我们还通过分享其权重以获得跨任务的知识来增强适配器的效率和性能。我们的结果表明,使用权重共享技术(总参数的4.4%)培训适配器可以匹配微调整个模型的性能。最后,我们提出了一个全面的分析,包括适配器和任务特定提示的组合以及V&L对适配器进行培训的影响。我们的代码可用于:https://github.com/ylsung/vl_adapter。
translated by 谷歌翻译
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。
translated by 谷歌翻译
在回答问题时,人类会利用跨不同模式可用的信息来综合一致,完整的思想链(COT)。在深度学习模型(例如大规模语言模型)的情况下,这个过程通常是黑匣子。最近,科学问题基准已用于诊断AI系统的多跳推理能力和解释性。但是,现有数据集无法为答案提供注释,或仅限于仅文本模式,小尺度和有限的域多样性。为此,我们介绍了科学问题答案(SQA),这是一个新的基准,由〜21k的多模式多种选择问题组成,其中包含各种科学主题和答案的注释,并提供相应的讲座和解释。我们进一步设计语言模型,以学习将讲座和解释作为思想链(COT),以模仿回答SQA问题时的多跳上推理过程。 SQA在语言模型中展示了COT的实用性,因为COT将问题的答案绩效提高了1.20%的GPT-3和3.99%的unifiedqa。我们还探索了模型的上限,以通过喂食输入中的那些来利用解释;我们观察到它将GPT-3的少量性能提高了18.96%。我们的分析进一步表明,与人类类似的语言模型受益于解释,从较少的数据中学习并仅使用40%的数据实现相同的性能。
translated by 谷歌翻译
Visual understanding goes well beyond object recognition. With one glance at an image, we can effortlessly imagine the world beyond the pixels: for instance, we can infer people's actions, goals, and mental states. While this task is easy for humans, it is tremendously difficult for today's vision systems, requiring higher-order cognition and commonsense reasoning about the world. We formalize this task as Visual Commonsense Reasoning. Given a challenging question about an image, a machine must answer correctly and then provide a rationale justifying its answer.Next, we introduce a new dataset, VCR, consisting of 290k multiple choice QA problems derived from 110k movie scenes. The key recipe for generating non-trivial and highquality problems at scale is Adversarial Matching, a new approach to transform rich annotations into multiple choice questions with minimal bias. Experimental results show that while humans find VCR easy (over 90% accuracy), state-of-the-art vision models struggle (∼45%).To move towards cognition-level understanding, we present a new reasoning engine, Recognition to Cognition Networks (R2C), that models the necessary layered inferences for grounding, contextualization, and reasoning. R2C helps narrow the gap between humans and machines (∼65%); still, the challenge is far from solved, and we provide analysis that suggests avenues for future work.
translated by 谷歌翻译