Many real-world problems are inherently multimodal, from the communicative modalities humans use to express social and emotional states to the force, proprioception, and visual sensors ubiquitous on robots. While there has been an explosion of interest in multimodal representation learning, these methods are still largely focused on a small set of modalities, primarily in the language, vision, and audio space. In order to accelerate generalization towards diverse and understudied modalities, this paper studies efficient representation learning for high-modality scenarios. Since adding new models for every new modality or task becomes prohibitively expensive, a critical technical challenge is heterogeneity quantification: how can we measure which modalities encode similar information and interactions in order to permit parameter sharing with previous modalities? We propose two new information-theoretic metrics for heterogeneity quantification: (1) modality heterogeneity studies how similar 2 modalities $\{X_1,X_2\}$ are by measuring how much information can be transferred from $X_1$ to $X_2$, while (2) interaction heterogeneity studies how similarly pairs of modalities $\{X_1,X_2\}, \{X_3,X_4\}$ interact by measuring how much interaction information can be transferred from $\{X_1,X_2\}$ to $\{X_3,X_4\}$. We show the importance of these proposed metrics in high-modality scenarios as a way to automatically prioritize the fusion of modalities that contain unique information or interactions. The result is a single model, HighMMT, that scales up to $10$ modalities and $15$ tasks from $5$ different research areas. Not only does HighMMT outperform prior methods on the tradeoff between performance and efficiency, it also demonstrates a crucial scaling behavior: performance continues to improve with each modality added, and transfers to entirely new modalities and tasks during fine-tuning.

拥有丰富的多模式内在语言是人类智力的重要组成部分，它可以实现多种必要的核心认知功能，例如多模式预测，翻译和生成。在有意识的图灵机（CTM）的基础上，这是Blum and Blum提出的意识模型（2021），我们描述了一种称为Brainish的多模式的Desiderata，包括单词，图像，音频和感觉，结合了CTM的表示形式处理器用来相互通信。我们在通过多模式人工智能的镜头进行操作之前定义了大脑的语法和语义，这是一个充满活力的研究区域，研究了处理和关联异质信号信息所需的计算工具。我们学习的一般框架涉及设计（1）单峰编码器以细分并表示非模态数据，（2）协调的表示空间，该空间将和编写单峰特征与多模式输入的整体含义相关联，以及（3）解码器以映射多模式表示形式。进入预测（用于融合）或原始数据（用于翻译或生成）。通过讨论为了在CTM中实现意识以及实施简单版本的脑部和评估其在几个现实世界图像，文本和文本和检索任务上展示智能的能力，通过讨论对沟通和协调的脑力至关重要音频数据集，我们认为这种内在语言对于机器智力和意识模型的进步将很重要。

我们可以训练一个能够处理多个模态和数据集的单个变压器模型，同时分享几乎所有的学习参数？我们呈现Polyvit，一种培训的模型，在图像，音频和视频上接受了讲述这个问题。通过在单一的方式上培训不同的任务，我们能够提高每个任务的准确性，并在5个标准视频和音频分类数据集中实现最先进的结果。多种模式和任务上的共同训练Polyvit会导致一个更具参数效率的模型，并学习遍历多个域的表示。此外，我们展示了实施的共同培训和实用，因为我们不需要调整数据集的每个组合的超级参数，但可以简单地调整来自标准的单一任务培训。

使用文本，图像，音频，视频等多种方式的多模式深度学习系统，与单独的方式（即单向）系统相比，显示出更好的性能。多式联机学习涉及多个方面：表示，翻译，对齐，融合和共同学习。在当前多式联机学习状态下，假设是在训练和测试时间期间存在，对齐和无噪声。然而，在现实世界的任务中，通常，观察到一个或多个模式丢失，嘈杂，缺乏注释数据，具有不可靠的标签，并且在训练或测试中稀缺，或两者都稀缺。这种挑战是由称为多式联合学习的学习范例解决的。通过使用模态之间的知识传输，包括其表示和预测模型，通过从另一个（资源丰富的）方式利用来自另一（资源丰富的）模型的知识来帮助实现（资源差）模型的建模。共同学习是一个新兴地区，没有专注的评论，明确地关注共同学习所解决的所有挑战。为此，在这项工作中，我们对新兴的多式联合学习领域提供了全面的调查，尚未完整探讨。我们审查实施的实施，以克服一个或多个共同学习挑战，而不明确地将它们视为共同学习挑战。我们基于共同学习和相关实施解决的挑战，展示了多式联合学习的综合分类。用于包括最新的技术与一些应用程序和数据集一起审查。我们的最终目标是讨论挑战和观点以及未来工作的重要思想和方向，我们希望对整个研究界的有益，重点关注这一令人兴奋的领域。

Astounding results from Transformer models on natural language tasks have intrigued the vision community to study their application to computer vision problems. Among their salient benefits, Transformers enable modeling long dependencies between input sequence elements and support parallel processing of sequence as compared to recurrent networks e.g., Long short-term memory (LSTM). Different from convolutional networks, Transformers require minimal inductive biases for their design and are naturally suited as set-functions. Furthermore, the straightforward design of Transformers allows processing multiple modalities (e.g., images, videos, text and speech) using similar processing blocks and demonstrates excellent scalability to very large capacity networks and huge datasets. These strengths have led to exciting progress on a number of vision tasks using Transformer networks. This survey aims to provide a comprehensive overview of the Transformer models in the computer vision discipline. We start with an introduction to fundamental concepts behind the success of Transformers i.e., self-attention, large-scale pre-training, and bidirectional feature encoding. We then cover extensive applications of transformers in vision including popular recognition tasks (e.g., image classification, object detection, action recognition, and segmentation), generative modeling, multi-modal tasks (e.g., visual-question answering, visual reasoning, and visual grounding), video processing (e.g., activity recognition, video forecasting), low-level vision (e.g., image super-resolution, image enhancement, and colorization) and 3D analysis (e.g., point cloud classification and segmentation). We compare the respective advantages and limitations of popular techniques both in terms of architectural design and their experimental value. Finally, we provide an analysis on open research directions and possible future works. We hope this effort will ignite further interest in the community to solve current challenges towards the application of transformer models in computer vision.

State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any other visual concept. Learning directly from raw text about images is a promising alternative which leverages a much broader source of supervision. We demonstrate that the simple pre-training task of predicting which caption goes with which image is an efficient and scalable way to learn SOTA image representations from scratch on a dataset of 400 million (image, text) pairs collected from the internet. After pre-training, natural language is used to reference learned visual concepts (or describe new ones) enabling zero-shot transfer of the model to downstream tasks. We study the performance of this approach by benchmarking on over 30 different existing computer vision datasets, spanning tasks such as OCR, action recognition in videos, geo-localization, and many types of fine-grained object classification. The model transfers non-trivially to most tasks and is often competitive with a fully supervised baseline without the need for any dataset specific training. For instance, we match the accuracy of the original ResNet-50 on ImageNet zero-shot without needing to use any of the 1.28 million training examples it was trained on. We release our code and pre-trained model weights at https://github.com/OpenAI/CLIP.

来自视频数据的多模态学习最近看过，因为它允许在没有人为注释的情况下培训语义有意义的嵌入，从而使得零射击检索和分类等任务。在这项工作中，我们提出了一种多模态，模态无政府主义融合变压器方法，它学会在多个模态之间交换信息，例如视频，音频和文本，并将它们集成到加入的多模态表示中，以获取聚合的嵌入多模态时间信息。我们建议培训系统的组合丢失，单个模态以及成对的方式，明确地留出任何附加组件，如位置或模态编码。在测试时间时，产生的模型可以处理和融合任意数量的输入模态。此外，变压器的隐式属性允许处理不同长度的输入。为了评估所提出的方法，我们在大规模HOWASET上培训模型，并评估四个具有挑战性的基准数据集上产生的嵌入空间获得最先进的视频检索和零射击视频动作定位。

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。

Multimodal models are becoming increasingly effective, in part due to unified components, such as the Transformer architecture. However, multimodal models still often consist of many task- and modality-specific pieces and training procedures. For example, CLIP (Radford et al., 2021) trains independent text and image towers via a contrastive loss. We explore an additional unification: the use of a pure pixel-based model to perform image, text, and multimodal tasks. Our model is trained with contrastive loss alone, so we call it CLIP-Pixels Only (CLIPPO). CLIPPO uses a single encoder that processes both regular images and text rendered as images. CLIPPO performs image-based tasks such as retrieval and zero-shot image classification almost as well as CLIP, with half the number of parameters and no text-specific tower or embedding. When trained jointly via image-text contrastive learning and next-sentence contrastive learning, CLIPPO can perform well on natural language understanding tasks, without any word-level loss (language modelling or masked language modelling), outperforming pixel-based prior work. Surprisingly, CLIPPO can obtain good accuracy in visual question answering, simply by rendering the question and image together. Finally, we exploit the fact that CLIPPO does not require a tokenizer to show that it can achieve strong performance on multilingual multimodal retrieval without

我们使用无卷积的变压器架构提出了一种从未标记数据学习多式式表示的框架。具体而言，我们的视频音频文本变压器（Vatt）将原始信号作为输入提取，提取丰富的多式化表示，以使各种下游任务受益。我们使用多模式对比损失从头划线训练Vatt端到端，并通过视频动作识别，音频事件分类，图像分类和文本到视频检索的下游任务评估其性能。此外，我们通过共享三种方式之间的重量来研究模型 - 无话的单骨架变压器。我们表明，无卷积VATT优于下游任务中的最先进的Convnet架构。特别是，Vatt的视觉变压器在动力学-400上实现82.1％的高精度82.1％，在动力学-600，72.7％的动力学-700上的72.7％，以及时间的时间，新的记录，在避免受监督的预训练时，新的记录。通过从头划伤训练相同的变压器，转移到图像分类导致图像分类导致78.7％的ImageNet精度为64.7％，尽管视频和图像之间的域间差距，我们的模型概括了我们的模型。 Vatt的音雅音频变压器还通过在没有任何监督的预训练的情况下在Audioset上实现39.4％的地图来设置基于波形的音频事件识别的新记录。 Vatt的源代码是公开的。

最近，自我监督的表示学习（SSRL）在计算机视觉，语音，自然语言处理（NLP）以及最近的其他类型的模式（包括传感器的时间序列）中引起了很多关注。自我监督学习的普及是由传统模型通常需要大量通知数据进行培训的事实所驱动的。获取带注释的数据可能是一个困难且昂贵的过程。已经引入了自我监督的方法，以通过使用从原始数据自由获得的监督信号对模型进行判别预训练来提高训练数据的效率。与现有的对SSRL的评论不同，该评论旨在以单一模式为重点介绍CV或NLP领域的方法，我们旨在为时间数据提供对多模式自我监督学习方法的首次全面审查。为此，我们1）提供现有SSRL方法的全面分类，2）通过定义SSRL框架的关键组件来引入通用管道，3）根据其目标功能，网络架构和潜在应用程序，潜在的应用程序，潜在的应用程序，比较现有模型， 4）查看每个类别和各种方式中的现有多模式技术。最后，我们提出了现有的弱点和未来的机会。我们认为，我们的工作对使用多模式和/或时间数据的域中SSRL的要求有了一个观点

视觉变压器正在成为解决计算机视觉问题的强大工具。最近的技术还证明了超出图像域之外的变压器来解决许多与视频相关的任务的功效。其中，由于其广泛的应用，人类的行动识别是从研究界受到特别关注。本文提供了对动作识别的视觉变压器技术的首次全面调查。我们朝着这个方向分析并总结了现有文献和新兴文献，同时突出了适应变形金刚以进行动作识别的流行趋势。由于其专业应用，我们将这些方法统称为``动作变压器''。我们的文献综述根据其架构，方式和预期目标为动作变压器提供了适当的分类法。在动作变压器的背景下，我们探讨了编码时空数据，降低维度降低，框架贴片和时空立方体构造以及各种表示方法的技术。我们还研究了变压器层中时空注意的优化，以处理更长的序列，通常通过减少单个注意操作中的令牌数量。此外，我们还研究了不同的网络学习策略，例如自我监督和零局学习，以及它们对基于变压器的行动识别的相关损失。这项调查还总结了在具有动作变压器重要基准的评估度量评分方面取得的进步。最后，它提供了有关该研究方向的挑战，前景和未来途径的讨论。

Transformer models have shown great success handling long-range interactions, making them a promising tool for modeling video. However they lack inductive biases and scale quadratically with input length. These limitations are further exacerbated when dealing with the high dimensionality introduced with the temporal dimension. While there are surveys analyzing the advances of Transformers for vision, none focus on an in-depth analysis of video-specific designs. In this survey we analyze main contributions and trends of works leveraging Transformers to model video. Specifically, we delve into how videos are handled as input-level first. Then, we study the architectural changes made to deal with video more efficiently, reduce redundancy, re-introduce useful inductive biases, and capture long-term temporal dynamics. In addition we provide an overview of different training regimes and explore effective self-supervised learning strategies for video. Finally, we conduct a performance comparison on the most common benchmark for Video Transformers (i.e., action classification), finding them to outperform 3D ConvNets even with less computational complexity.

Inspired by progress in large-scale language modeling, we apply a similar approach towards building a single generalist agent beyond the realm of text outputs. The agent, which we refer to as Gato, works as a multi-modal, multi-task, multi-embodiment generalist policy. The same network with the same weights can play Atari, caption images, chat, stack blocks with a real robot arm and much more, deciding based on its context whether to output text, joint torques, button presses, or other tokens. In this report we describe the model and the data, and document the current capabilities of Gato.

Humans perceive the world by concurrently processing and fusing high-dimensional inputs from multiple modalities such as vision and audio. Machine perception models, in stark contrast, are typically modality-specific and optimised for unimodal benchmarks, and hence late-stage fusion of final representations or predictions from each modality (`late-fusion') is still a dominant paradigm for multimodal video classification. Instead, we introduce a novel transformer based architecture that uses `fusion bottlenecks' for modality fusion at multiple layers. Compared to traditional pairwise self-attention, our model forces information between different modalities to pass through a small number of bottleneck latents, requiring the model to collate and condense the most relevant information in each modality and only share what is necessary. We find that such a strategy improves fusion performance, at the same time reducing computational cost. We conduct thorough ablation studies, and achieve state-of-the-art results on multiple audio-visual classification benchmarks including Audioset, Epic-Kitchens and VGGSound. All code and models will be released.

We present Masked Audio-Video Learners (MAViL) to train audio-visual representations. Our approach learns with three complementary forms of self-supervision: (1) reconstruction of masked audio and video input data, (2) intra- and inter-modal contrastive learning with masking, and (3) self-training by reconstructing joint audio-video contextualized features learned from the first two objectives. Pre-training with MAViL not only enables the model to perform well in audio-visual classification and retrieval tasks but also improves representations of each modality in isolation, without using information from the other modality for fine-tuning or inference. Empirically, MAViL sets a new state-of-the-art on AudioSet (53.1 mAP) and VGGSound (67.1% accuracy). For the first time, a self-supervised audio-visual model outperforms ones that use external supervision on these benchmarks. Code will be available soon.

Biological systems perceive the world by simultaneously processing high-dimensional inputs from modalities as diverse as vision, audition, touch, proprioception, etc. The perception models used in deep learning on the other hand are designed for individual modalities, often relying on domainspecific assumptions such as the local grid structures exploited by virtually all existing vision models. These priors introduce helpful inductive biases, but also lock models to individual modalities. In this paper we introduce the Perceiver -a model that builds upon Transformers and hence makes few architectural assumptions about the relationship between its inputs, but that also scales to hundreds of thousands of inputs, like ConvNets. The model leverages an asymmetric attention mechanism to iteratively distill inputs into a tight latent bottleneck, allowing it to scale to handle very large inputs. We show that this architecture is competitive with or outperforms strong, specialized models on classification tasks across various modalities: images, point clouds, audio, video, and video+audio. The Perceiver obtains performance comparable to ResNet-50 and ViT on ImageNet without 2D convolutions by directly attending to 50,000 pixels. It is also competitive in all modalities in AudioSet.

多模型对现实世界应用的承诺激发了可视化和理解其内部力学的研究，其最终目标是使利益相关者能够可视化模型行为，执行模型调试并促进对机器学习模型的信任。但是，现代的多模型模型通常是黑盒神经网络，这使得了解其内部力学变得具有挑战性。我们如何能在这些模型中可视化多模式相互作用的内部建模？我们的论文旨在通过提出Multiviz来填补这一空白，这是一种通过将可解释性问题分为4个阶段来分析多模型模型行为的方法：（1）单峰的重要性：每种模式如何有助于下游建模和预测，（2）交叉交叉。 - 模式相互作用：不同模态如何相互关系，（3）多模式表示：如何在决策级特征中表示单峰和跨模式的交互作用，以及（4）多模式预测：决策级特征如何组成以制造一个预言。 Multiviz旨在在不同的模式，模型，任务和研究领域进行操作。通过对6个现实世界任务的8个训练模型的实验，我们表明，Multiviz中的互补阶段共同使用户能够（1）模拟模型预测，（2）将可解释的概念分配给功能，（3）对模型错误分析执行错误分析，（4）使用错误分析到调试模型的见解。 Multiviz公开可用，将定期使用新的解释工具和指标进行更新，并欢迎社区的意见。

人类的物体感知能力令人印象深刻，当试图开发具有类似机器人的解决方案时，这变得更加明显。从人类如何将视觉和触觉用于对象感知和相关任务的灵感中，本文总结了机器人应用的多模式对象感知的当前状态。它涵盖了生物学灵感，传感器技术，数据集以及用于对象识别和掌握的感觉数据处理的各个方面。首先，概述了多模式对象感知的生物学基础。然后讨论了传感技术和数据收集策略。接下来，介绍了主要计算方面的介绍，突出显示了每个主要应用领域的一些代表性文章，包括对象识别，传输学习以及对象操纵和掌握。最后，在每个领域的当前进步中，本文概述了有希望的新研究指示。

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。