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.

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.

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 present in this paper a new architecture, named Convolutional vision Transformer (CvT), that improves Vision Transformer (ViT) in performance and efficiency by introducing convolutions into ViT to yield the best of both designs. This is accomplished through two primary modifications: a hierarchy of Transformers containing a new convolutional token embedding, and a convolutional Transformer block leveraging a convolutional projection. These changes introduce desirable properties of convolutional neural networks (CNNs) to the ViT architecture (i.e. shift, scale, and distortion invariance) while maintaining the merits of Transformers (i.e. dynamic attention, global context, and better generalization). We validate CvT by conducting extensive experiments, showing that this approach achieves state-of-the-art performance over other Vision Transformers and ResNets on ImageNet-1k, with fewer parameters and lower FLOPs. In addition, performance gains are maintained when pretrained on larger datasets (e.g. ImageNet-22k) and fine-tuned to downstream tasks. Pretrained on ImageNet-22k, our CvT-W24 obtains a top-1 accuracy of 87.7% on the ImageNet-1k val set. Finally, our results show that the positional encoding, a crucial component in existing Vision Transformers, can be safely removed in our model, simplifying the design for higher resolution vision tasks. Code will be released at https: //github.com/leoxiaobin/CvT.

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。

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.

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。

过去一年目睹了将变压器模块应用于视力问题的快速发展。虽然一些研究人员已经证明，基于变压器的模型享有有利的拟合数据能力，但仍然越来越多的证据，表明这些模型尤其在训练数据受到限制时遭受过度拟合。本文通过执行逐步操作来提供实证研究，逐步运输基于变压器的模型到基于卷积的模型。我们在过渡过程中获得的结果为改善视觉识别提供了有用的消息。基于这些观察，我们提出了一个名为VIRFormer的新架构，该体系结构从“视觉友好的变压器”中缩写。具有相同的计算复杂度，在想象集分类精度方面，VISFormer占据了基于变压器的基于卷积的模型，并且当模型复杂性较低或训练集较小时，优势变得更加重要。代码可在https://github.com/danczs/visformer中找到。

为了实现不断增长的准确性，通常会开发大型和复杂的神经网络。这样的模型需要高度的计算资源，因此不能在边缘设备上部署。由于它们在几个应用领域的有用性，建立资源有效的通用网络非常感兴趣。在这项工作中，我们努力有效地结合了CNN和变压器模型的优势，并提出了一种新的有效混合体系结构。特别是在EDGENEXT中，我们引入了分裂深度转置注意力（SDTA）编码器，该编码器将输入张量分解为多个通道组，并利用深度旋转以及跨通道维度的自我注意力，以隐含地增加接受场并编码多尺度特征。我们在分类，检测和分割任务上进行的广泛实验揭示了所提出的方法的优点，优于相对较低的计算要求的最先进方法。我们具有130万参数的EDGENEXT模型在Imagenet-1k上达到71.2 \％TOP-1的精度，超过移动设备的绝对增益为2.2 \％，而拖鞋减少了28 \％。此外，我们具有560万参数的EDGENEXT模型在Imagenet-1k上达到了79.4 \％TOP-1的精度。代码和模型可在https://t.ly/_vu9上公开获得。

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

随着变压器作为语言处理的标准及其在计算机视觉方面的进步，参数大小和培训数据的数量相应地增长。许多人开始相信，因此，变形金刚不适合少量数据。这种趋势引起了人们的关注，例如：某些科学领域中数据的可用性有限，并且排除了该领域研究资源有限的人。在本文中，我们旨在通过引入紧凑型变压器来提出一种小规模学习的方法。我们首次表明，具有正确的尺寸，卷积令牌化，变压器可以避免在小数据集上过度拟合和优于最先进的CNN。我们的模型在模型大小方面具有灵活性，并且在获得竞争成果的同时，参数可能仅为0.28亿。当在CIFAR-10上训练Cifar-10，只有370万参数训练时，我们的最佳模型可以达到98％的准确性，这是与以前的基于变形金刚的模型相比，数据效率的显着提高，比其他变压器小于10倍，并且是15％的大小。在实现类似性能的同时，重新NET50。 CCT还表现优于许多基于CNN的现代方法，甚至超过一些基于NAS的方法。此外，我们在Flowers-102上获得了新的SOTA，具有99.76％的TOP-1准确性，并改善了Imagenet上现有基线（82.71％精度，具有29％的VIT参数）以及NLP任务。我们针对变压器的简单而紧凑的设计使它们更可行，可以为那些计算资源和/或处理小型数据集的人学习，同时扩展了在数据高效变压器中的现有研究工作。我们的代码和预培训模型可在https://github.com/shi-labs/compact-transformers上公开获得。

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。

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.

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。

卷积神经网络（CNN）是用于计算机视觉的主要的深神经网络（DNN）架构。最近，变压器和多层的Perceptron（MLP）的基础型号，如视觉变压器和MLP-MILER，开始引领新的趋势，因为它们在想象成分类任务中显示出了有希望的结果。在本文中，我们对这些DNN结构进行了实证研究，并试图了解他们各自的利弊。为了确保公平的比较，我们首先开发一个名为SPACH的统一框架，可以采用单独的空间和通道处理模块。我们在SPACH框架下的实验表明，所有结构都可以以适度的规模实现竞争性能。但是，当网络大小缩放时，它们展示了独特的行为。根据我们的调查结果，我们建议使用卷积和变压器模块的混合模型。由此产生的Hybrid-MS-S +模型实现了83.9％的前1个精度，63米参数和12.3g拖薄。它已与具有复杂设计的SOTA模型相提并论。代码和模型在https://github.com/microsoft/spach上公开使用。

视觉变压器（VIT）显示了计算机视觉任务的快速进步，在各种基准上取得了令人鼓舞的结果。但是，由于参数和模型设计的数量大量，例如注意机制，基于VIT的模型通常比轻型卷积网络慢。因此，为实时应用程序部署VIT特别具有挑战性，尤其是在资源受限的硬件（例如移动设备）上。最近的努力试图通过网络体系结构搜索或与Mobilenet块的混合设计来降低VIT的计算复杂性，但推理速度仍然不令人满意。这导致了一个重要的问题：变形金刚在获得高性能的同时可以像Mobilenet一样快吗？为了回答这一点，我们首先重新审视基于VIT的模型中使用的网络体系结构和运营商，并确定效率低下的设计。然后，我们引入了一个尺寸一致的纯变压器（无需Mobilenet块）作为设计范式。最后，我们执行以延迟驱动的缩小，以获取一系列称为EfficityFormer的最终模型。广泛的实验表明，在移动设备上的性能和速度方面，有效形式的优势。我们最快的型号，EfficientFormer-L1，在ImagEnet-1k上获得$ 79.2 \％$ $ TOP-1的准确性，仅$ 1.6 $ MS推理潜伏期在iPhone 12上（与Coreml一起编译），该{运行速度与MobileNetV2 $ \ Times Times 1.4 $（ $ 1.6 $ MS，$ 74.7 \％$ top-1），我们最大的型号EfficientFormer-L7，获得了$ 83.3 \％$精度，仅$ 7.0 $ MS延迟。我们的工作证明，正确设计的变压器可以在移动设备上达到极低的延迟，同时保持高性能。

尽管图像变形金刚与计算机视觉任务中的卷积神经网络显示出竞争性结果，但缺乏诸如区域的电感偏见仍然在模型效率方面构成问题，尤其是对于嵌入式应用程序而言。在这项工作中，我们通过引入注意力面具以将空间位置纳入自我发挥作用来解决这个问题。局部依赖性有效地捕获了掩盖的注意力头，以及由未掩盖的注意力头部捕获的全球依赖性。随着蒙版注意力图像变压器 - MAIT，与CAIT相比，TOP -1的准确性提高了1.7％，与SWIN相比，吞吐量更少，吞吐量提高了1.5倍。使用注意力面罩编码局部性是模型的不可知论，因此它适用于整体，分层或其他新型变压器体系结构。

基于自我注意力的模型，例如视觉变压器（VIT），已经成为计算机视觉中卷积神经网络（CNN）的一种非常有竞争力的建筑。尽管越来越高的变体具有更高的识别精度，但由于自我注意力的二次复杂性，现有的VIT通常在计算和模型大小中要求。尽管已重新引入了最近的CNN的几种成功设计选择（例如，卷积和分层多阶段结构）已重新引入最近的VIT，但它们仍然不足以满足移动设备的有限资源要求。这激发了最近根据最先进的Mobilenet-V2开发光线的尝试，但仍然留下了性能差距。在这项工作中，在这个研究不足的方向上进一步推动了Edgevits，这是一个新的轻巧vits家族，这首先使基于注意力的视觉模型能够与最佳轻巧的CNN竞争，这准确性和设备效率。这是通过基于自我注意力和卷积的最佳整合而引入高度成本效益的本地 - 全球局（LGL）信息交换瓶颈来实现的。对于设备青年的评估，我们不再依赖诸如拖船或参数的不准确代理，而是采用一种实用的方法来直接专注于设备延迟，以及首次首次提供能源效率。具体而言，我们表明，当考虑准确性的延迟和准确性 - 能量折衷时，我们的模型是帕累托最佳的，在几乎所有情况下都严格占据了其他VIT并与最有效的CNN竞争的严格优势。代码可从https://github.com/saic-fi/edgevit获得。

Convolutional architectures have proven extremely successful for vision tasks. Their hard inductive biases enable sample-efficient learning, but come at the cost of a potentially lower performance ceiling. Vision Transformers (ViTs) rely on more flexible self-attention layers, and have recently outperformed CNNs for image classification. However, they require costly pre-training on large external datasets or distillation from pretrained convolutional networks. In this paper, we ask the following question: is it possible to combine the strengths of these two architectures while avoiding their respective limitations? To this end, we introduce gated positional self-attention (GPSA), a form of positional self-attention which can be equipped with a "soft" convolutional inductive bias. We initialize the GPSA layers to mimic the locality of convolutional layers, then give each attention head the freedom to escape locality by adjusting a gating parameter regulating the attention paid to position versus content information. The resulting convolutionallike ViT architecture, ConViT, outperforms the DeiT (Touvron et al., 2020) on ImageNet, while offering a much improved sample efficiency. We further investigate the role of locality in learning by first quantifying how it is encouraged in vanilla self-attention layers, then analyzing how it is escaped in GPSA layers. We conclude by presenting various ablations to better understand the success of the ConViT. Our code and models are released publicly at https://github.com/ facebookresearch/convit.