General perception systems such as Perceivers can process arbitrary modalities in any combination and are able to handle up to a few hundred thousand inputs. They achieve this generality by using exclusively global attention operations. This however hinders them from scaling up to the inputs sizes required to process raw high-resolution images or video. In this paper, we show that some degree of locality can be introduced back into these models, greatly improving their efficiency while preserving their generality. To scale them further, we introduce a self-supervised approach that enables learning dense low-dimensional positional embeddings for very large signals. We call the resulting model a Hierarchical Perceiver (HiP). In sum our contributions are: 1) scaling Perceiver-type models to raw high-resolution images and audio+video, 2) showing the feasibility of learning 1M+ positional embeddings from scratch using masked auto-encoding, 3) demonstrating competitive performance on raw data from ImageNet, AudioSet, PASCAL VOC, ModelNet40 and Kinetics datasets with the same exact, unchanged model and without specialized preprocessing or any tokenization.

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.

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。

While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention is either applied in conjunction with convolutional networks, or used to replace certain components of convolutional networks while keeping their overall structure in place. We show that this reliance on CNNs is not necessary and a pure transformer applied directly to sequences of image patches can perform very well on image classification tasks. When pre-trained on large amounts of data and transferred to multiple mid-sized or small image recognition benchmarks (ImageNet, CIFAR-100, VTAB, etc.), Vision Transformer (ViT) attains excellent results compared to state-of-the-art convolutional networks while requiring substantially fewer computational resources to train. 1

基于变压器的体系结构已在各种视觉域（最著名的图像和视频）中变得更具竞争力。虽然先前的工作已经孤立地研究了这些模式，但拥有一个共同的体系结构表明，人们可以训练单个统一模型以多种视觉方式。事先尝试进行统一建模通常使用针对视觉任务量身定制的体系结构，或与单个模态模型相比获得较差的性能。在这项工作中，我们表明可以使用蒙版的自动编码来在图像和视频上训练简单的视觉变压器，而无需任何标记的数据。该单个模型学习了与图像和视频基准上的单模式表示相当或更好的视觉表示，同时使用了更简单的体系结构。特别是，我们的单一预算模型可以进行审核，以在ImageNet上获得86.5％的速度，而在挑战性的事物V2视频基准测试中，可以实现75.3％的范围。此外，可以通过丢弃90％的图像和95％的视频补丁来学习该模型，从而实现非常快速的训练。

本文显示屏蔽的自动化器（MAE）是可扩展的自我监督学习者，用于计算机愿景。我们的MAE方法很简单：我们掩盖输入图像的随机补丁并重建缺失像素。它基于两个核心设计。首先，我们开发一个不对称的编码器解码器架构，其中编码器仅在掩码的可见子集（没有掩码令牌）上，以及重量解码器，该重量解码器从潜像和掩码令牌重建原始图像。其次，我们发现掩蔽了高比例的输入图像，例如，75％，产生非凡和有意义的自我监督任务。耦合这两种设计使我们能够有效且有效地培训大型模型：我们加速培训（3倍或更多）并提高准确性。我们可扩展的方法允许学习概括的高容量模型：例如，Vanilla Vit-Maxim模型在使用Imagenet-1K数据的方法中实现最佳准确性（87.8％）。下游任务中的转移性能优于监督预培训并显示有前途的缩放行为。

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.

本文研究了基于图像的蒙版自动编码器（MAE）的简单扩展，以从音频谱图中学习自我监督的表示。在MAE中的变压器编码器编码器设计之后，我们的Audio-MAE首先编码具有较高遮罩比的音频谱图斑块，仅通过编码器层馈入非掩盖令牌。然后，解码器重新订购并解码编码的上下文，并用掩码令牌填充，以重建输入频谱图。我们发现将局部窗户注意力纳入解码器是有益的，因为音频谱图在当地时间和频带中高度相关。然后，我们在目标数据集上以较低的掩模比微调编码器。从经验上讲，音频MAE在六个音频和语音分类任务上设定了新的最先进的性能，超过了使用外部监督预训练的其他最新模型。代码和模型将在https://github.com/facebookresearch/audiomae上。

我们呈现蒙版特征预测（MaskFeat），用于自我监督的视频模型的预训练。我们的方法首先随机地掩盖输入序列的一部分，然后预测蒙面区域的特征。我们研究五种不同类型的功能，找到面向导向渐变（HOG）的直方图，手工制作的特征描述符，在性能和效率方面尤其良好。我们观察到猪中的局部对比标准化对于良好的结果至关重要，这与使用HOG进行视觉识别的早期工作符合。我们的方法可以学习丰富的视觉知识和基于大规模的变压器的模型。在不使用额外的模型重量或监督的情况下，在未标记视频上预先培训的MaskFeat在动力学-400上使用MVIT-L达到86.7％的前所未有的结果，在动力学-600，88.3％上，88.3％，在动力学-700,88.8地图上SSV2上的75.0％。 MaskFeat进一步推广到图像输入，其可以被解释为具有单个帧的视频，并在想象中获得竞争结果。

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.

Can we leverage the audiovisual information already present in video to improve self-supervised representation learning? To answer this question, we study various pretraining architectures and objectives within the masked autoencoding framework, motivated by the success of similar methods in natural language and image understanding. We show that we can achieve significant improvements on audiovisual downstream classification tasks, surpassing the state-of-the-art on VGGSound and AudioSet. Furthermore, we can leverage our audiovisual pretraining scheme for multiple unimodal downstream tasks using a single audiovisual pretrained model. We additionally demonstrate the transferability of our representations, achieving state-of-the-art audiovisual results on Epic Kitchens without pretraining specifically for this dataset.

大型视力模型的无监督预训练方法已显示出可以提高下游监督任务的性能。为卫星图像开发类似的技术带来了重要的机会，因为未标记的数据很丰富，并且固有的时间和多光谱结构提供了途径，以进一步改善现有的训练策略。在本文中，我们提出了Satmae，这是基于蒙面自动编码器（MAE）的时间或多光谱卫星图像的预训练框架。为了利用时间信息，我们包括一个时间嵌入以及跨时间独立掩盖图像贴片。此外，我们证明将多光谱数据编码为具有不同光谱位置编码的频段组是有益的。我们的方法在基准数据集（最高$ \ uparrow $ 7 \％）上的监督学习绩效方面都对先前最先前的技术产生了强大的改进，以及在下游遥感任务（包括土地）上的转移学习绩效封面分类（最多$ \ uparrow $ 14 \％）和语义细分。

The combination of transformers and masked image modeling (MIM) pre-training framework has shown great potential in various vision tasks. However, the pre-training computational budget is too heavy and withholds the MIM from becoming a practical training paradigm. This paper presents FastMIM, a simple and generic framework for expediting masked image modeling with the following two steps: (i) pre-training vision backbones with low-resolution input images; and (ii) reconstructing Histograms of Oriented Gradients (HOG) feature instead of original RGB values of the input images. In addition, we propose FastMIM-P to progressively enlarge the input resolution during pre-training stage to further enhance the transfer results of models with high capacity. We point out that: (i) a wide range of input resolutions in pre-training phase can lead to similar performances in fine-tuning phase and downstream tasks such as detection and segmentation; (ii) the shallow layers of encoder are more important during pre-training and discarding last several layers can speed up the training stage with no harm to fine-tuning performance; (iii) the decoder should match the size of selected network; and (iv) HOG is more stable than RGB values when resolution transfers;. Equipped with FastMIM, all kinds of vision backbones can be pre-trained in an efficient way. For example, we can achieve 83.8%/84.1% top-1 accuracy on ImageNet-1K with ViT-B/Swin-B as backbones. Compared to previous relevant approaches, we can achieve comparable or better top-1 accuracy while accelerate the training procedure by $\sim$5$\times$. Code can be found in https://github.com/ggjy/FastMIM.pytorch.

We present Multiscale Vision Transformers (MViT) for video and image recognition, by connecting the seminal idea of multiscale feature hierarchies with transformer models. Multiscale Transformers have several channel-resolution scale stages. Starting from the input resolution and a small channel dimension, the stages hierarchically expand the channel capacity while reducing the spatial resolution. This creates a multiscale pyramid of features with early layers operating at high spatial resolution to model simple low-level visual information, and deeper layers at spatially coarse, but complex, high-dimensional features. We evaluate this fundamental architectural prior for modeling the dense nature of visual signals for a variety of video recognition tasks where it outperforms concurrent vision transformers that rely on large scale external pre-training and are 5-10× more costly in computation and parameters. We further remove the temporal dimension and apply our model for image classification where it outperforms prior work on vision transformers. Code is available at: https: //github.com/facebookresearch/SlowFast.

我们引入了一个自我监督的视觉表示模型BEIT，该模型代表来自图像变压器的双向编码器表示。在Bert在自然语言处理区域中开发后，我们提出了一项掩盖的图像建模任务，以预识视觉变压器。具体而言，每个图像在我们的预训练中具有两个视图，即图像贴片（例如16x16像素）和视觉令牌（即离散令牌）。我们首先将原始图像“将”“令牌化”到视觉令牌中。然后，我们随机掩盖了一些图像补丁并将其喂入骨干变压器中。预训练的目标是根据损坏的图像补丁恢复原始的视觉令牌。在预训练BEIT之后，我们通过将任务层附加在预审计的编码器上，直接通过将任务层附加到下游任务上的模型参数。图像分类和语义分割的实验结果表明，我们的模型通过以前的预训练方法实现了竞争结果。例如，基本大小的BEIT在Imagenet-1K上获得了83.2％的TOP-1精度，并以相同的设置优于划痕DEIT训练（81.8％）。此外，大尺寸的BEIT仅使用Imagenet-1K获得86.3％，即使在Imagenet-22K上进行预训练（85.2％），甚至超过了VIT-L。代码和预估计的模型可在https://aka.ms/beit上找到。

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.

蒙面的自动编码器是可扩展的视觉学习者，因为Mae \ Cite {He2022masked}的标题表明，视觉中的自我监督学习（SSL）可能会采用与NLP中类似的轨迹。具体而言，具有蒙版预测（例如BERT）的生成借口任务已成为NLP中的事实上的标准SSL实践。相比之下，他们的歧视性对应物（例如对比度学习）掩埋了视力中的生成方法的早期尝试；但是，蒙版图像建模的成功已恢复了屏蔽自动编码器（过去通常被称为DeNosing AutoCoder）。作为在NLP中与Bert弥合差距的一个里程碑，蒙面自动编码器吸引了对SSL在视觉及其他方面的前所未有的关注。这项工作对蒙面自动编码器进行了全面的调查，以洞悉SSL的有希望的方向。作为第一个使用蒙版自动编码器审查SSL的人，这项工作通过讨论其历史发展，最新进度以及对不同应用的影响，重点介绍其在视觉中的应用。

Convolutional Neural Networks (CNNs) are the go-to model for computer vision. Recently, attention-based networks, such as the Vision Transformer, have also become popular. In this paper we show that while convolutions and attention are both sufficient for good performance, neither of them are necessary. We present MLP-Mixer, an architecture based exclusively on multi-layer perceptrons (MLPs). MLP-Mixer contains two types of layers: one with MLPs applied independently to image patches (i.e. "mixing" the per-location features), and one with MLPs applied across patches (i.e. "mixing" spatial information). When trained on large datasets, or with modern regularization schemes, MLP-Mixer attains competitive scores on image classification benchmarks, with pre-training and inference cost comparable to state-of-the-art models. We hope that these results spark further research beyond the realms of well established CNNs and Transformers. 1

我们呈现Point-Bert，一种用于学习变压器的新范式，以概括BERT对3D点云的概念。灵感来自BERT，我们将屏蔽点建模（MPM）任务设计为预列火车点云变压器。具体地，我们首先将点云划分为几个本地点修补程序，并且具有离散变化性AutoEncoder（DVAE）的点云标记器被设计为生成包含有意义的本地信息的离散点令牌。然后，我们随机掩盖了一些输入点云的补丁并将它们送入骨干变压器。预训练目标是在销售器获得的点代币的监督下恢复蒙面地点的原始点令牌。广泛的实验表明，拟议的BERT风格的预训练策略显着提高了标准点云变压器的性能。配备了我们的预培训策略，我们表明，纯变压器架构对ModelNet40的准确性为93.8％，在ScanObjectnn的最艰难的设置上的准确性为83.1％，超越精心设计的点云模型，手工制作的设计更少。我们还证明，Point-Bert从新的任务和域中获悉的表示，我们的模型在很大程度上推动了几个射击点云分类任务的最先进。代码和预先训练的型号可在https://github.com/lulutang0608/pint -bert上获得

由于具有强大的代表性，变形金刚在包括自然语言处理（NLP），计算机视觉和语音识别在内的广泛应用中越来越受欢迎。但是，利用这种代表性的能力有效地需要大量的数据，强大的正则化或两者兼而有之以减轻过度拟合。最近，基于掩盖的自动编码器的自我监督预处理策略已解锁了变压器的功能，这些策略依赖于直接或从未掩盖的内容对比的掩蔽输入进行重建。这种预训练的策略已在NLP中的BERT模型，Speak2VEC模型中使用，最近在Vision中的MAE模型中，该模型迫使该模型使用自动编码相关的目标来了解输入不同部分中的内容之间的关系。在本文中，我们提出了一种小说但令人惊讶的简单替代内容，以预测内容的位置，而无需为其提供位置信息。这样做需要变压器仅凭内容就可以理解输入不同部分之间的位置关系。这相当于有效的实现，其中借口任务是每个输入令牌所有可能位置之间的分类问题。我们在视觉和语音基准上进行了实验，我们的方法对强有力的监督训练基准进行了改进，并且与现代的无监督/自我监督预审方法相媲美。我们的方法还可以使经过训练的变压器在没有位置嵌入的情况下胜过训练有完整位置信息的训练的变压器。