我们展示了如何通过基于关注的全球地图扩充任何卷积网络，以实现非本地推理。我们通过基于关注的聚合层替换为单个变压器块的最终平均池，重量贴片如何参与分类决策。我们使用2个参数（宽度和深度）使用简单的补丁卷积网络，使用简单的补丁的卷积网络插入学习的聚合层。与金字塔设计相比，该架构系列在所有层上维护输入补丁分辨率。它在准确性和复杂性之间产生了令人惊讶的竞争权衡，特别是在记忆消耗方面，如我们在各种计算机视觉任务所示：对象分类，图像分割和检测的实验所示。

Transformers have been recently adapted for large scale image classification, achieving high scores shaking up the long supremacy of convolutional neural networks. However the optimization of image transformers has been little studied so far. In this work, we build and optimize deeper transformer networks for image classification. In particular, we investigate the interplay of architecture and optimization of such dedicated transformers. We make two transformers architecture changes that significantly improve the accuracy of deep transformers. This leads us to produce models whose performance does not saturate early with more depth, for instance we obtain 86.5% top-1 accuracy on Imagenet when training with no external data, we thus attain the current SOTA with less FLOPs and parameters. Moreover, our best model establishes the new state of the art on Imagenet with Reassessed labels and Imagenet-V2 / match frequency, in the setting with no additional training data. We share our code and models 1 .

We introduce submodel co-training, a regularization method related to co-training, self-distillation and stochastic depth. Given a neural network to be trained, for each sample we implicitly instantiate two altered networks, ``submodels'', with stochastic depth: we activate only a subset of the layers. Each network serves as a soft teacher to the other, by providing a loss that complements the regular loss provided by the one-hot label. Our approach, dubbed cosub, uses a single set of weights, and does not involve a pre-trained external model or temporal averaging. Experimentally, we show that submodel co-training is effective to train backbones for recognition tasks such as image classification and semantic segmentation. Our approach is compatible with multiple architectures, including RegNet, ViT, PiT, XCiT, Swin and ConvNext. Our training strategy improves their results in comparable settings. For instance, a ViT-B pretrained with cosub on ImageNet-21k obtains 87.4% top-1 acc. @448 on ImageNet-val.

Recently, neural networks purely based on attention were shown to address image understanding tasks such as image classification. These highperforming vision transformers are pre-trained with hundreds of millions of images using a large infrastructure, thereby limiting their adoption.In this work, we produce competitive convolution-free transformers by training on Imagenet only. We train them on a single computer in less than 3 days. Our reference vision transformer (86M parameters) achieves top-1 accuracy of 83.1% (single-crop) on ImageNet with no external data.More importantly, we introduce a teacher-student strategy specific to transformers. It relies on a distillation token ensuring that the student learns from the teacher through attention. We show the interest of this token-based distillation, especially when using a convnet as a teacher. This leads us to report results competitive with convnets for both Imagenet (where we obtain up to 85.2% accuracy) and when transferring to other tasks. We share our code and models.

Recently, neural networks purely based on attention were shown to address image understanding tasks such as image classification. These highperforming vision transformers are pre-trained with hundreds of millions of images using a large infrastructure, thereby limiting their adoption.In this work, we produce competitive convolutionfree transformers trained on ImageNet only using a single computer in less than 3 days. Our reference vision transformer (86M parameters) achieves top-1 accuracy of 83.1% (single-crop) on ImageNet with no external data.We also introduce a teacher-student strategy specific to transformers. It relies on a distillation token ensuring that the student learns from the teacher through attention, typically from a convnet teacher. The learned transformers are competitive (85.2% top-1 acc.) with the state of the art on ImageNet, and similarly when transferred to other tasks. We will share our code and models.

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。

We design a family of image classification architectures that optimize the trade-off between accuracy and efficiency in a high-speed regime. Our work exploits recent findings in attention-based architectures, which are competitive on highly parallel processing hardware. We revisit principles from the extensive literature on convolutional neural networks to apply them to transformers, in particular activation maps with decreasing resolutions. We also introduce the attention bias, a new way to integrate positional information in vision transformers.As a result, we propose LeVIT: a hybrid neural network for fast inference image classification. We consider different measures of efficiency on different hardware platforms, so as to best reflect a wide range of application scenarios. Our extensive experiments empirically validate our technical choices and show they are suitable to most architectures. Overall, LeViT significantly outperforms existing convnets and vision transformers with respect to the speed/accuracy tradeoff. For example, at 80% ImageNet top-1 accuracy, LeViT is 5 times faster than EfficientNet on CPU. We release the code at https: //github.com/facebookresearch/LeViT.

诸如对象检测和分割等密集的计算机视觉任务需要有效的多尺度特征表示，用于检测或分类具有不同大小的对象或区域。虽然卷积神经网络（CNNS）是这种任务的主导架构，但最近引入了视觉变压器（VITS）的目标是将它们替换为骨干。类似于CNN，VITS构建一个简单的多级结构（即，细致粗略），用于使用单尺度补丁进行多尺度表示。在这项工作中，通过从现有变压器的不同角度来看，我们探索了多尺度补丁嵌入和多路径结构，构建了多路径视觉变压器（MPVIT）。 MPVIT通过使用重叠的卷积贴片嵌入，将相同尺寸〜（即，序列长度，序列长度，序列长度的序列长度）嵌入不同尺度的斑块。然后，通过多个路径独立地将不同尺度的令牌独立地馈送到变压器编码器，并且可以聚合产生的特征，使得能够在相同特征级别的精细和粗糙的特征表示。由于多样化，多尺寸特征表示，我们的MPVits从微小〜（5m）缩放到基础〜（73米）一直在想象成分，对象检测，实例分段上的最先进的视觉变压器来实现卓越的性能，和语义细分。这些广泛的结果表明，MPVIT可以作为各种视觉任务的多功能骨干网。代码将在\ url {https://git.io/mpvit}上公开可用。

在本文中，我们将多尺度视觉变压器（MVIT）作为图像和视频分类的统一架构，以及对象检测。我们提出了一种改进的MVIT版本，它包含分解的相对位置嵌入和残余汇集连接。我们以五种尺寸实例化此架构，并评估Imagenet分类，COCO检测和动力学视频识别，在此优先效果。我们进一步比较了MVITS的汇集注意力来窗口注意力机制，其中它在准确性/计算中优于后者。如果没有钟声，MVIT在3个域中具有最先进的性能：ImageNet分类的准确性为88.8％，Coco对象检测的56.1盒AP和动力学-400视频分类的86.1％。代码和模型将公开可用。

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.

在最近的计算机视觉研究中，Vision Transformer（VIT）的出现迅速彻底改变了各种建筑设计工作：VIT使用自然语言处理中发现的自我注意力实现了最新的图像分类性能，而MLP-Mixer实现了使用简单多层感知器的竞争性能。相比之下，一些研究还表明，精心重新设计的卷积神经网络（CNN）可以实现与VIT相当的先进性能，而无需诉诸这些新想法。在这种背景下，越来越多的感应偏见适合计算机视觉。在这里，我们提出了Sequencer，这是VIT的一种新颖且具有竞争力的体系结构，可为这些问题提供新的看法。与VIT不同，音序器使用LSTM而不是自我发项层模型的远程依赖性。我们还提出了二维版本的音序器模块，其中LSTM分解为垂直和水平LSTM，以增强性能。尽管它很简单，但一些实验表明，Sequencer表现出色：Sequencer2d-L，具有54m参数，​​仅在Imagenet-1K上实现了84.6％的TOP-1精度。不仅如此，我们还表明它具有良好的可传递性和在双分辨率波段上具有强大的分辨率适应性。

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.

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

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（VIT）用作强大的视觉模型。与卷积神经网络不同，在前几年主导视觉研究，视觉变压器享有捕获数据中的远程依赖性的能力。尽管如此，任何变压器架构的组成部分，自我关注机制都存在高延迟和低效的内存利用，使其不太适合高分辨率输入图像。为了缓解这些缺点，分层视觉模型在非交错的窗口上局部使用自我关注。这种放松会降低输入尺寸的复杂性;但是，它限制了横窗相互作用，损害了模型性能。在本文中，我们提出了一种新的班次不变的本地注意层，称为查询和参加（QNA），其以重叠的方式聚集在本地输入，非常类似于卷积。 QNA背后的关键想法是介绍学习的查询，这允许快速高效地实现。我们通过将其纳入分层视觉变压器模型来验证我们的层的有效性。我们展示了速度和内存复杂性的改进，同时实现了与最先进的模型的可比准确性。最后，我们的图层尺寸尤其良好，窗口大小，需要高于X10的内存，而不是比现有方法更快。

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。

Vision transformer (ViT) models exhibit substandard optimizability. In particular, they are sensitive to the choice of optimizer (AdamW vs. SGD), optimizer hyperparameters, and training schedule length. In comparison, modern convolutional neural networks are easier to optimize. Why is this the case? In this work, we conjecture that the issue lies with the patchify stem of ViT models, which is implemented by a stride-p p×p convolution (p = 16 by default) applied to the input image. This large-kernel plus large-stride convolution runs counter to typical design choices of convolutional layers in neural networks. To test whether this atypical design choice causes an issue, we analyze the optimization behavior of ViT models with their original patchify stem versus a simple counterpart where we replace the ViT stem by a small number of stacked stride-two 3×3 convolutions. While the vast majority of computation in the two ViT designs is identical, we find that this small change in early visual processing results in markedly different training behavior in terms of the sensitivity to optimization settings as well as the final model accuracy. Using a convolutional stem in ViT dramatically increases optimization stability and also improves peak performance (by ∼1-2% top-1 accuracy on ImageNet-1k), while maintaining flops and runtime. The improvement can be observed across the wide spectrum of model complexities (from 1G to 36G flops) and dataset scales (from ImageNet-1k to ImageNet-21k). These findings lead us to recommend using a standard, lightweight convolutional stem for ViT models in this regime as a more robust architectural choice compared to the original ViT model design.

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

对象检测是用于测试预先训练的网络参数的中央下游任务是否达到益处，例如提高准确度或训练速度。当新架构（如视觉变压器（VIT）模型到达时，物体检测方法的复杂性可以使该基准是非微不足道的。这些困难（例如，架构不相容，慢训练，高记忆消耗，未知的培训公式等）已经阻止了最近通过标准VIT模型进行了基准测试转移学习的研究。在本文中，我们提出了克服这些挑战的培训技术，使得使用标准的VT模型作为面膜R-CNN的骨干。这些工具促进了我们研究的主要目标：我们比较五种Vit初始化，包括最近的最先进的自我监督的学习方法，监督初始化和强大的随机初始化基线。我们的研究结果表明，最近基于掩蔽的无监督学习方法可能是在COCO的令人信服的转移学习改进，将箱子AP增加到4％（绝对）的监督和先前自我监督的预训练方法。此外，基于掩蔽的初始化比例更好，随着模型尺寸的增加而增长的提高。

在本文中，我们通过利用视觉数据中的空间稀疏性提出了一种新的模型加速方法。我们观察到，视觉变压器中的最终预测仅基于最有用的令牌的子集，这足以使图像识别。基于此观察，我们提出了一个动态的令牌稀疏框架，以根据加速视觉变压器的输入逐渐和动态地修剪冗余令牌。具体而言，我们设计了一个轻量级预测模块，以估计给定当前功能的每个令牌的重要性得分。该模块被添加到不同的层中以层次修剪冗余令牌。尽管该框架的启发是我们观察到视觉变压器中稀疏注意力的启发，但我们发现自适应和不对称计算的想法可能是加速各种体系结构的一般解决方案。我们将我们的方法扩展到包括CNN和分层视觉变压器在内的层次模型，以及更复杂的密集预测任务，这些任务需要通过制定更通用的动态空间稀疏框架，并具有渐进性的稀疏性和非对称性计算，用于不同空间位置。通过将轻质快速路径应用于少量的特征，并使用更具表现力的慢速路径到更重要的位置，我们可以维护特征地图的结构，同时大大减少整体计算。广泛的实验证明了我们框架对各种现代体系结构和不同视觉识别任务的有效性。我们的结果清楚地表明，动态空间稀疏为模型加速提供了一个新的，更有效的维度。代码可从https://github.com/raoyongming/dynamicvit获得