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.

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。

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

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.

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。

This paper does not describe a novel method. Instead, it studies a straightforward, incremental, yet must-know baseline given the recent progress in computer vision: selfsupervised learning for Vision Transformers (ViT). While the training recipes for standard convolutional networks have been highly mature and robust, the recipes for ViT are yet to be built, especially in the self-supervised scenarios where training becomes more challenging. In this work, we go back to basics and investigate the effects of several fundamental components for training self-supervised ViT. We observe that instability is a major issue that degrades accuracy, and it can be hidden by apparently good results. We reveal that these results are indeed partial failure, and they can be improved when training is made more stable. We benchmark ViT results in MoCo v3 and several other selfsupervised frameworks, with ablations in various aspects. We discuss the currently positive evidence as well as challenges and open questions. We hope that this work will provide useful data points and experience for future research.

在本文中，我们询问视觉变形金刚（VIT）是否可以作为改善机器学习模型对抗逃避攻击的对抗性鲁棒性的基础结构。尽管较早的作品集中在改善卷积神经网络上，但我们表明VIT也非常适合对抗训练以实现竞争性能。我们使用自定义的对抗训练配方实现了这一目标，该配方是在Imagenet数据集的一部分上使用严格的消融研究发现的。与卷积相比，VIT的规范培训配方建议强大的数据增强，部分是为了补偿注意力模块的视力归纳偏置。我们表明，该食谱在用于对抗训练时可实现次优性能。相比之下，我们发现省略所有重型数据增强，并添加一些额外的零件（$ \ varepsilon $ -Warmup和更大的重量衰减），从而大大提高了健壮的Vits的性能。我们表明，我们的配方在完整的Imagenet-1k上概括了不同类别的VIT体系结构和大规模模型。此外，调查了模型鲁棒性的原因，我们表明，在使用我们的食谱时，在训练过程中产生强烈的攻击更加容易，这会在测试时提高鲁棒性。最后，我们通过提出一种量化对抗性扰动的语义性质并强调其与模型的鲁棒性的相关性来进一步研究对抗训练的结果。总体而言，我们建议社区应避免将VIT的规范培训食谱转换为在对抗培训的背景下进行强大的培训和重新思考常见的培训选择。

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 .

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。

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

视觉变形金刚最近的成功是在图像识别中挥舞着卷积神经网络（CNN）的长期优势。具体而言，就稳健性而言，最近的研究发现，无论训练设置如何，变压器本质上比CNN更强大。此外，人们认为，变形金刚的这种优越性应该在很大程度上被认为是他们的自我注意力型建筑本身。在本文中，我们通过密切研究变压器的设计来质疑这种信念。我们的发现导致了三种高效的体系结构设计，以提高鲁棒性，但很简单，可以在几行代码中实现，即a）修补输入图像，b）扩大内核大小，c）降低激活层和归一化层。将这些组件融合在一起，我们能够构建纯CNN体系结构，而没有任何类似注意力的操作，这些操作比变形金刚更强大，甚至更健壮。我们希望这项工作可以帮助社区更好地了解强大的神经体系结构的设计。该代码可在https://github.com/ucsc-vlaa/robustcnn上公开获得。

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.

视觉变压器（VIT）已被证明可以在广泛的视觉应用中获得高度竞争性的性能，例如图像分类，对象检测和语义图像分割。与卷积神经网络相比，通常发现视觉变压器的较弱的电感偏差会在较小的培训数据集上培训时，会增加对模型正则化或数据增强的依赖（简称为“ AUGREG”）。我们进行了一项系统的实证研究，以便更好地了解培训数据，AUGREG，模型大小和计算预算之间的相互作用。作为这项研究的一个结果，我们发现增加的计算和AUGREG的组合可以产生与在数量级上训练的模型相同的训练数据的模型：我们在公共Imagenet-21K数据集中培训各种尺寸的VIT模型在较大的JFT-300M数据集上匹配或超越其对手的培训。

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。

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.

In this work, we present a new network design paradigm. Our goal is to help advance the understanding of network design and discover design principles that generalize across settings. Instead of focusing on designing individual network instances, we design network design spaces that parametrize populations of networks. The overall process is analogous to classic manual design of networks, but elevated to the design space level. Using our methodology we explore the structure aspect of network design and arrive at a low-dimensional design space consisting of simple, regular networks that we call RegNet. The core insight of the RegNet parametrization is surprisingly simple: widths and depths of good networks can be explained by a quantized linear function. We analyze the RegNet design space and arrive at interesting findings that do not match the current practice of network design. The RegNet design space provides simple and fast networks that work well across a wide range of flop regimes. Under comparable training settings and flops, the RegNet models outperform the popular Effi-cientNet models while being up to 5× faster on GPUs.

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.

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。