We propose a new neural network design paradigm Reversible Column Network (RevCol). The main body of RevCol is composed of multiple copies of subnetworks, named columns respectively, between which multi-level reversible connections are employed. Such architectural scheme attributes RevCol very different behavior from conventional networks: during forward propagation, features in RevCol are learned to be gradually disentangled when passing through each column, whose total information is maintained rather than compressed or discarded as other network does. Our experiments suggest that CNN-style RevCol models can achieve very competitive performances on multiple computer vision tasks such as image classification, object detection and semantic segmentation, especially with large parameter budget and large dataset. For example, after ImageNet-22K pre-training, RevCol-XL obtains 88.2% ImageNet-1K accuracy. Given more pre-training data, our largest model RevCol-H reaches 90.0% on ImageNet-1K, 63.8% APbox on COCO detection minival set, 61.0% mIoU on ADE20k segmentation. To our knowledge, it is the best COCO detection and ADE20k segmentation result among pure (static) CNN models. Moreover, as a general macro architecture fashion, RevCol can also be introduced into transformers or other neural networks, which is demonstrated to improve the performances in both computer vision and NLP tasks. We release code and models at https://github.com/megvii-research/RevCol

视觉变压器由于能够捕获图像中的长期依赖性的能力而成功地应用于图像识别任务。但是，变压器与现有卷积神经网络（CNN）之间的性能和计算成本仍然存在差距。在本文中，我们旨在解决此问题，并开发一个网络，该网络不仅可以超越规范变压器，而且可以超越高性能卷积模型。我们通过利用变压器来捕获长期依赖性和CNN来建模本地特征，从而提出了一个新的基于变压器的混合网络。此外，我们将其扩展为获得一个称为CMT的模型家族，比以前的基于卷积和基于变压器的模型获得了更好的准确性和效率。特别是，我们的CMT-S在ImageNet上获得了83.5％的TOP-1精度，而在拖鞋上的拖曳率分别比现有的DEIT和EficitiveNet小14倍和2倍。拟议的CMT-S还可以很好地概括CIFAR10（99.2％），CIFAR100（91.7％），花（98.7％）以及其他具有挑战性的视觉数据集，例如可可（44.3％地图），计算成本较小。

视觉变压器的最新进展在基于点产生自我注意的新空间建模机制驱动的各种任务中取得了巨大成功。在本文中，我们表明，视觉变压器背后的关键要素，即输入自适应，远程和高阶空间相互作用，也可以通过基于卷积的框架有效地实现。我们介绍了递归封闭式卷积（$ \ textit {g}^\ textit {n} $ conv），该卷积{n} $ conv）与封闭的卷积和递归设计执行高阶空间交互。新操作是高度灵活和可定制的，它与卷积的各种变体兼容，并将自我注意的两阶相互作用扩展到任意订单，而无需引入大量额外的计算。 $ \ textit {g}^\ textit {n} $ conv可以用作插件模块，以改善各种视觉变压器和基于卷积的模型。根据该操作，我们构建了一个名为Hornet的新型通用视觉骨干家族。关于ImageNet分类，可可对象检测和ADE20K语义分割的广泛实验表明，大黄蜂的表现优于Swin变形金刚，并具有相似的整体体系结构和训练配置的明显边距。大黄蜂还显示出对更多训练数据和更大模型大小的有利可伸缩性。除了在视觉编码器中的有效性外，我们还可以将$ \ textit {g}^\ textit {n} $ conv应用于特定于任务的解码器，并始终通过较少的计算来提高密集的预测性能。我们的结果表明，$ \ textIt {g}^\ textit {n} $ conv可以成为视觉建模的新基本模块，可有效结合视觉变形金刚和CNN的优点。代码可从https://github.com/raoyongming/hornet获得

变压器是一种基于关注的编码器解码器架构，彻底改变了自然语言处理领域。灵感来自这一重大成就，最近在将变形式架构调整到计算机视觉（CV）领域的一些开创性作品，这已经证明了他们对各种简历任务的有效性。依靠竞争力的建模能力，与现代卷积神经网络相比在本文中，我们已经为三百不同的视觉变压器进行了全面的审查，用于三个基本的CV任务（分类，检测和分割），提出了根据其动机，结构和使用情况组织这些方法的分类。 。由于培训设置和面向任务的差异，我们还在不同的配置上进行了评估了这些方法，以便于易于和直观的比较而不是各种基准。此外，我们已经揭示了一系列必不可少的，但可能使变压器能够从众多架构中脱颖而出，例如松弛的高级语义嵌入，以弥合视觉和顺序变压器之间的差距。最后，提出了三个未来的未来研究方向进行进一步投资。

We present the Group Propagation Vision Transformer (GPViT): a novel nonhierarchical (i.e. non-pyramidal) transformer model designed for general visual recognition with high-resolution features. High-resolution features (or tokens) are a natural fit for tasks that involve perceiving fine-grained details such as detection and segmentation, but exchanging global information between these features is expensive in memory and computation because of the way self-attention scales. We provide a highly efficient alternative Group Propagation Block (GP Block) to exchange global information. In each GP Block, features are first grouped together by a fixed number of learnable group tokens; we then perform Group Propagation where global information is exchanged between the grouped features; finally, global information in the updated grouped features is returned back to the image features through a transformer decoder. We evaluate GPViT on a variety of visual recognition tasks including image classification, semantic segmentation, object detection, and instance segmentation. Our method achieves significant performance gains over previous works across all tasks, especially on tasks that require high-resolution outputs, for example, our GPViT-L3 outperforms Swin Transformer-B by 2.0 mIoU on ADE20K semantic segmentation with only half as many parameters. Code and pre-trained models are available at https://github.com/ChenhongyiYang/GPViT .

视觉变压器（VIT）最近在一系列计算机视觉任务中占据了主导地位，但训练数据效率低下，局部语义表示能力较低，而没有适当的电感偏差。卷积神经网络（CNNS）固有地捕获了区域感知语义，激发了研究人员将CNN引入VIT的架构中，以为VIT提供理想的诱导偏见。但是，嵌入在VIT中的微型CNN实现的位置是否足够好？在本文中，我们通过深入探讨混合CNNS/VIT的宏观结构如何增强层次VIT的性能。特别是，我们研究了令牌嵌入层，别名卷积嵌入（CE）的作用，并系统地揭示了CE如何在VIT中注入理想的感应偏置。此外，我们将最佳CE配置应用于最近发布的4个最先进的Vits，从而有效地增强了相应的性能。最后，释放了一个有效的混合CNN/VIT家族，称为CETNET，可以用作通用的视觉骨架。具体而言，CETNET在Imagenet-1K上获得了84.9％的TOP-1准确性（从头开始训练），可可基准上的48.6％的盒子地图和ADE20K上的51.6％MIOU，从而显着提高了相应的最新态度的性能。艺术基线。

视觉识别的“咆哮20S”开始引入视觉变压器（VITS），这将被取代的Cummnets作为最先进的图像分类模型。另一方面，vanilla vit，当应用于一般计算机视觉任务等对象检测和语义分割时面临困难。它是重新引入多个ConvNet Priors的等级变压器（例如，Swin变压器），使变压器实际上可作为通用视觉骨干网，并在各种视觉任务上展示了显着性能。然而，这种混合方法的有效性仍然在很大程度上归功于变压器的内在优越性，而不是卷积的固有感应偏差。在这项工作中，我们重新审视设计空间并测试纯粹的Convnet可以实现的限制。我们逐渐“现代化”标准Reset朝着视觉变压器的设计设计，并发现几个有助于沿途绩效差异的关键组件。此探索的结果是一个纯粹的ConvNet型号被称为ConvNext。完全由标准的Convnet模块构建，ConvNexts在准确性和可扩展性方面与变压器竞争，实现了87.8％的ImageNet Top-1精度和表现优于COCO检测和ADE20K分割的Swin变压器，同时保持了标准Convnet的简单性和效率。

Compared to the great progress of large-scale vision transformers (ViTs) in recent years, large-scale models based on convolutional neural networks (CNNs) are still in an early state. This work presents a new large-scale CNN-based foundation model, termed InternImage, which can obtain the gain from increasing parameters and training data like ViTs. Different from the recent CNNs that focus on large dense kernels, InternImage takes deformable convolution as the core operator, so that our model not only has the large effective receptive field required for downstream tasks such as detection and segmentation, but also has the adaptive spatial aggregation conditioned by input and task information. As a result, the proposed InternImage reduces the strict inductive bias of traditional CNNs and makes it possible to learn stronger and more robust patterns with large-scale parameters from massive data like ViTs. The effectiveness of our model is proven on challenging benchmarks including ImageNet, COCO, and ADE20K. It is worth mentioning that InternImage-H achieved the new record 65.4 mAP on COCO test-dev. The code will be released at https://github.com/OpenGVLab/InternImage.

我们介绍克斯内变压器，一种高效且有效的变压器的骨干，用于通用视觉任务。变压器设计的具有挑战性的问题是，全球自我关注来计算成本昂贵，而局部自我关注经常限制每个令牌的相互作用。为了解决这个问题，我们开发了以平行的横向和垂直条纹在水平和垂直条纹中计算自我关注的交叉形窗口自我关注机制，通过将输入特征分成相等的条纹而获得的每个条纹宽度。我们提供了条纹宽度效果的数学分析，并改变变压器网络的不同层的条纹宽度，这在限制计算成本时实现了强大的建模能力。我们还介绍了本地增强的位置编码（LEPE），比现有的编码方案更好地处理本地位置信息。 LEPE自然支持任意输入分辨率，因此对下游任务特别有效和友好。 CSWIN变压器并入其具有这些设计和分层结构，展示了普通愿景任务的竞争性能。具体来说，它在ImageNet-1K上实现了85.4 \％Top-1精度，而无需任何额外的培训数据或标签，53.9盒AP和46.4掩模AP，ADE20K语义分割任务上的52.2 Miou，超过以前的状态 - 在类似的拖鞋设置下，艺术品+1.2，+2.0，+1.4和+2.0分别为+1.2，+2.0，+1.4和+2.0。通过在较大的数据集Imagenet-21k上进行前预先预订，我们在Ave20K上实现了87.5％的成像-1K和高分性能，55.7 miou。代码和模型可在https://github.com/microsoft/cswin-transformer中找到。

本文介绍了一个简单的MLP架构，CycleMLP，这是一种多功能骨干，用于视觉识别和密集的预测。与现代MLP架构相比，例如MLP混合器，RESMLP和GMLP，其架构与图像尺寸相关，因此在物体检测和分割中不可行，与现代方法相比具有两个优点。 （1）它可以应对各种图像尺寸。 （2）通过使用本地窗口，它可以实现对图像大小的线性计算复杂性。相比之下，由于完全空间连接，以前的MLP具有$ O（n ^ 2）$计算。我们构建一系列模型，超越现有的MLP，甚至最先进的基于变压器的模型，例如，使用较少的参数和拖鞋。我们扩展了类似MLP的模型的适用性，使它们成为密集预测任务的多功能骨干。 CycleMLP在对象检测，实例分割和语义细分上实现了竞争结果。特别是，Cyclemlp-tiny优于3.3％Miou在Ade20K数据集中的速度较少，具有较少的拖鞋。此外，CycleMLP还在Imagenet-C数据集上显示出优异的零射鲁布利。代码可以在https://github.com/shoufachen/cyclemlp获得。

本文探讨了贝尔视觉变压器预训练的更好的码本。最近的工作成功地转移了从NLP到视野领域的BERT预训练。它直接采用一个简单的离散VAE作为视觉销售器，但尚未考虑由此产生的视觉令牌的语义水平。相比之下，NLP字段中的离散令牌是自然的高度语义。这种差异激励我们学习一个感知码本。我们惊奇地找到了一个简单而有效的想法：在DVAE训练期间强制执行感知相似性。我们证明，所提出的感知码本生成的视觉令牌确实表现出更好的语义含义，随后有助于预训练在各种下游任务中实现卓越的转移性能。例如，我们在Imagenet-1K上实现了84.5前1个精度，vit-B骨干，优于竞争方法Beit +1.3，具有相同的训练纪元。它还可以通过+1.3框AP和+1.0掩模AP，在ADE20K上的语义细分，在ADE20K上提高对象检测和分割任务的性能，+1.0 miou，代码和型号将在\ url {https：// github.com/microsoft/peco}。

This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision. Challenges in adapting Transformer from language to vision arise from differences between the two domains, such as large variations in the scale of visual entities and the high resolution of pixels in images compared to words in text. To address these differences, we propose a hierarchical Transformer whose representation is computed with Shifted windows. The shifted windowing scheme brings greater efficiency by limiting self-attention computation to non-overlapping local windows while also allowing for cross-window connection. This hierarchical architecture has the flexibility to model at various scales and has linear computational complexity with respect to image size. These qualities of Swin Transformer make it compatible with a broad range of vision tasks, including image classification (87.3 top-1 accuracy on ImageNet-1K) and dense prediction tasks such as object detection (58.7 box AP and 51.1 mask AP on COCO testdev) and semantic segmentation (53.5 mIoU on ADE20K val). Its performance surpasses the previous state-of-theart by a large margin of +2.7 box AP and +2.6 mask AP on COCO, and +3.2 mIoU on ADE20K, demonstrating the potential of Transformer-based models as vision backbones. The hierarchical design and the shifted window approach also prove beneficial for all-MLP architectures. The code and models are publicly available at https://github. com/microsoft/Swin-Transformer.

最近的进展表明，使用对比图像文本对的大规模预训练可以是从自然语言监督的高质量视觉表演学习的有前途的替代方案。从更广泛的监督来源受益，这种新的范例展示了对下游分类任务和数据集的令人印象深刻的可转移性。然而，从图像文本对中学习的知识转移到更复杂的密集预测任务的问题几乎没有访问过。在这项工作中，我们通过隐式和明确地利用来自剪辑的预先训练的知识来提出了一种新的密集预测框架。具体地，我们将剪辑中的原始图像文本匹配问题转换为像素文本匹配问题，并使用像素文本分数图来指导致密预测模型的学习。通过进一步使用图像中的上下文信息来提示语言模型，我们能够促进我们的模型来更好地利用预先接受训练的知识。我们的方法是模型 - 不可行的，它可以应用于任意密集的预测系统和各种预先训练的视觉底座，包括夹模型和想象成预先训练的模型。广泛的实验证明了我们对语义分割，对象检测和实例分段任务的方法的卓越性能。代码可在https://github.com/raoyongming/denseclip获得

本文解决了由多头自我注意力（MHSA）中高计算/空间复杂性引起的视觉变压器的低效率缺陷。为此，我们提出了层次MHSA（H-MHSA），其表示以层次方式计算。具体而言，我们首先将输入图像分为通常完成的补丁，每个补丁都被视为令牌。然后，拟议的H-MHSA学习本地贴片中的令牌关系，作为局部关系建模。然后，将小贴片合并为较大的贴片，H-MHSA对少量合并令牌的全局依赖性建模。最后，汇总了本地和全球专注的功能，以获得具有强大表示能力的功能。由于我们仅在每个步骤中计算有限数量的令牌的注意力，因此大大减少了计算负载。因此，H-MHSA可以在不牺牲细粒度信息的情况下有效地模拟令牌之间的全局关系。使用H-MHSA模块合并，我们建立了一个基于层次的变压器网络的家族，即HAT-NET。为了证明在场景理解中HAT-NET的优越性，我们就基本视觉任务进行了广泛的实验，包括图像分类，语义分割，对象检测和实例细分。因此，HAT-NET为视觉变压器提供了新的视角。可以在https://github.com/yun-liu/hat-net上获得代码和预估计的模型。

香草自我注意的机制固有地依赖于预定和坚定的计算维度。这种僵化的性限制了它具有面向上下文的概括，可以带来更多的上下文提示和全球表示。为了减轻此问题，我们提出了一种可扩展的自我注意（SSA）机制，该机制利用两个缩放因素来释放查询，键和价值矩阵的维度，同时使它们不符合输入。这种可伸缩性可获得面向上下文的概括并增强对象灵敏度，从而将整个网络推向准确性和成本之间的更有效的权衡状态。此外，我们提出了一个基于窗口的自我注意事项（IWSA），该自我注意力（IWSA）通过重新合并独立的值代币并从相邻窗口中汇总空间信息来建立非重叠区域之间的相互作用。通过交替堆叠SSA和IWSA，可扩展的视觉变压器（可伸缩率）在通用视觉任务中实现最先进的性能。例如，在Imagenet-1K分类中，可伸缩率S的表现优于双胞胎-SVT-S，而Swin-T则比1.4％。

视觉表示学习是解决各种视力问题的关键。依靠开创性的网格结构先验，卷积神经网络（CNN）已成为大多数深视觉模型的事实上的标准架构。例如，经典的语义分割方法通常采用带有编码器编码器体系结构的完全横向卷积网络（FCN）。编码器逐渐减少了空间分辨率，并通过更大的接受场来学习更多抽象的视觉概念。由于上下文建模对于分割至关重要，因此最新的努力一直集中在通过扩张（即极度）卷积或插入注意力模块来增加接受场。但是，基于FCN的体系结构保持不变。在本文中，我们旨在通过将视觉表示学习作为序列到序列预测任务来提供替代观点。具体而言，我们部署纯变压器以将图像编码为一系列贴片，而无需局部卷积和分辨率减少。通过在变压器的每一层中建立的全球环境，可以学习更强大的视觉表示形式，以更好地解决视力任务。特别是，我们的细分模型（称为分割变压器（SETR））在ADE20K上擅长（50.28％MIOU，这是提交当天测试排行榜中的第一个位置），Pascal环境（55.83％MIOU），并在CityScapes上达到竞争成果。此外，我们制定了一个分层局部全球（HLG）变压器的家族，其特征是窗户内的本地关注和跨窗户的全球性专注于层次结构和金字塔架构。广泛的实验表明，我们的方法在各种视觉识别任务（例如，图像分类，对象检测和实例分割和语义分割）上实现了吸引力的性能。

Vision Transformers have shown great promise recently for many vision tasks due to the insightful architecture design and attention mechanism. By revisiting the self-attention responses in Transformers, we empirically observe two interesting issues. First, Vision Transformers present a queryirrelevant behavior at deep layers, where the attention maps exhibit nearly consistent contexts in global scope, regardless of the query patch position (also head-irrelevant). Second, the attention maps are intrinsically sparse, few tokens dominate the attention weights; introducing the knowledge from ConvNets would largely smooth the attention and enhance the performance. Motivated by above observations, we generalize self-attention formulation to abstract a queryirrelevant global context directly and further integrate the global context into convolutions. The resulting model, a Fully Convolutional Vision Transformer (i.e., FCViT), purely consists of convolutional layers and firmly inherits the merits of both attention mechanism and convolutions, including dynamic property, weight sharing, and short- and long-range feature modeling, etc. Experimental results demonstrate the effectiveness of FCViT. With less than 14M parameters, our FCViT-S12 outperforms related work ResT-Lite by 3.7% top1 accuracy on ImageNet-1K. When scaling FCViT to larger models, we still perform better than previous state-of-the-art ConvNeXt with even fewer parameters. FCViT-based models also demonstrate promising transferability to downstream tasks, like object detection, instance segmentation, and semantic segmentation. Codes and models are made available at: https://github.com/ma-xu/FCViT.

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.

多层erceptron（MLP），作为出现的第一个神经网络结构，是一个大的击中。但是由硬件计算能力和数据集的大小限制，它一旦沉没了数十年。在此期间，我们目睹了从手动特征提取到带有局部接收领域的CNN的范式转变，以及基于自我关注机制的全球接收领域的变换。今年（2021年），随着MLP混合器的推出，MLP已重新进入敏捷，并吸引了计算机视觉界的广泛研究。与传统的MLP进行比较，它变得更深，但改变了完全扁平化以补丁平整的输入。鉴于其高性能和较少的需求对视觉特定的感应偏见，但社区无法帮助奇迹，将MLP，最简单的结构与全球接受领域，但没有关注，成为一个新的电脑视觉范式吗？为了回答这个问题，本调查旨在全面概述视觉深层MLP模型的最新发展。具体而言，我们从微妙的子模块设计到全局网络结构，我们审查了这些视觉深度MLP。我们比较了不同网络设计的接收领域，计算复杂性和其他特性，以便清楚地了解MLP的开发路径。调查表明，MLPS的分辨率灵敏度和计算密度仍未得到解决，纯MLP逐渐发展朝向CNN样。我们建议，目前的数据量和计算能力尚未准备好接受纯的MLP，并且人工视觉指导仍然很重要。最后，我们提供了开放的研究方向和可能的未来作品的分析。我们希望这项努力能够点燃社区的进一步兴趣，并鼓励目前为神经网络进行更好的视觉量身定制设计。

We propose focal modulation networks (FocalNets in short), where self-attention (SA) is completely replaced by a focal modulation mechanism for modeling token interactions in vision. Focal modulation comprises three components: (i) hierarchical contextualization, implemented using a stack of depth-wise convolutional layers, to encode visual contexts from short to long ranges, (ii) gated aggregation to selectively gather contexts for each query token based on its content, and (iii) element-wise modulation or affine transformation to inject the aggregated context into the query. Extensive experiments show FocalNets outperform the state-of-the-art SA counterparts (e.g., Swin and Focal Transformers) with similar computational costs on the tasks of image classification, object detection, and segmentation. Specifically, FocalNets with tiny and base size achieve 82.3% and 83.9% top-1 accuracy on ImageNet-1K. After pretrained on ImageNet-22K in 224 resolution, it attains 86.5% and 87.3% top-1 accuracy when finetuned with resolution 224 and 384, respectively. When transferred to downstream tasks, FocalNets exhibit clear superiority. For object detection with Mask R-CNN, FocalNet base trained with 1\times outperforms the Swin counterpart by 2.1 points and already surpasses Swin trained with 3\times schedule (49.0 v.s. 48.5). For semantic segmentation with UPerNet, FocalNet base at single-scale outperforms Swin by 2.4, and beats Swin at multi-scale (50.5 v.s. 49.7). Using large FocalNet and Mask2former, we achieve 58.5 mIoU for ADE20K semantic segmentation, and 57.9 PQ for COCO Panoptic Segmentation. Using huge FocalNet and DINO, we achieved 64.3 and 64.4 mAP on COCO minival and test-dev, respectively, establishing new SoTA on top of much larger attention-based models like Swinv2-G and BEIT-3. Code and checkpoints are available at https://github.com/microsoft/FocalNet.