我们介绍了贴片采样时间表（PSS）的概念，该概念在训练过程中每批次使用的视觉变压器（VIT）贴片的数量变化。由于对于大多数视觉目标（例如，分类），所有补丁都不同样重要，因此我们认为，不太重要的补丁可以用于较少的训练迭代中，从而导致较短的训练时间，对性能的影响最小。此外，我们观察到，使用PSS的训练可以使VIT在推理过程中对更宽的贴片采样范围更强。这允许在推理过程中进行吞吐量和准确性之间的细粒度，动态的权衡。我们使用PSSS在VIT上评估Imagenet的VIT，均通过从头开始训练并使用重建损耗函数进行了预训练。对于预训练的模型，与使用所有斑块相比，我们的分类准确性降低了0.26％（从25小时到17小时）降低了0.26％。代码，模型检查点和日志可在https://github.com/bradmcdanel/pss上找到。

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.

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

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.

虽然最先进的视觉变压器模型实现了图像分类的有希望的结果，但它们是非常昂贵的并且需要许多GFLOPS。尽管可以通过减少网络中的令牌数量来降低视觉变压器的GFLOPS，但是没有对所有输入图像的最佳设置。因此，在这项工作中，我们引入了可分辨率的无参数自适应令牌采样（ATS）模块，可以插入任何现有的视觉变压器架构。通过评分和自适应采样重要令牌，在视觉变压器上实现视觉变压器。结果，令牌的数量不再静态，但是每个输入图像都变化。通过将ATS集成为当前变压器块内的附加层，我们可以将它们转换为具有自适应令牌的更高效的视觉变压器。由于ATS是一种无参数模块，因此它可以作为即插即用模块添加到从货架上的预制视觉变压器中，从而在没有任何额外训练的情况下减少他们的GFLOP。但是，由于其可分辨动的设计，人们还可以培训配有ATS的视觉变压器。通过将其添加到多个最先进的视觉变压器，我们在想象成数据集上进行评估。我们的评估表明，通过将计算成本（GFLOPS）降低37％，在保留准确性时，该模块通过降低了37％，提高了最先进的模块。

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

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 .

视觉变压器已经证明了在各种视觉任务中胜过CNN的潜力。但是这些模型的计算和内存要求禁止在许多应用中使用它们，尤其是依赖高分辨率图像的应用程序，例如医学图像分类。更有效地训练VIT的努力过于复杂，需要进行建筑变化或复杂的培训方案。在这项工作中，我们表明可以通过随机删除输入图像贴片来有效地以高分辨率进行标准VIT模型。这种简单的方法（PatchDropout）在标准的自然图像数据集（例如ImageNet）中将拖鞋和内存减少至少50％，而这些节省仅随图像尺寸而增加。在高分辨率医疗数据集CSAW上，我们使用PatchDropout可节省5倍的计算和内存，并提高性能。对于具有固定计算或内存预算的从业人员，PatchDropout可以选择图像分辨率，超参数或模型大小以使其从模型中获得最大的性能。

Vision Transformers convert images to sequences by slicing them into patches. The size of these patches controls a speed/accuracy tradeoff, with smaller patches leading to higher accuracy at greater computational cost, but changing the patch size typically requires retraining the model. In this paper, we demonstrate that simply randomizing the patch size at training time leads to a single set of weights that performs well across a wide range of patch sizes, making it possible to tailor the model to different compute budgets at deployment time. We extensively evaluate the resulting model, which we call FlexiViT, on a wide range of tasks, including classification, image-text retrieval, open-world detection, panoptic segmentation, and semantic segmentation, concluding that it usually matches, and sometimes outperforms, standard ViT models trained at a single patch size in an otherwise identical setup. Hence, FlexiViT training is a simple drop-in improvement for ViT that makes it easy to add compute-adaptive capabilities to most models relying on a ViT backbone architecture. Code and pre-trained models are available at https://github.com/google-research/big_vision

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。

视觉变换器将每个图像分成具有固定长度的令牌序列，并以与自然语言处理中的单词相同的方式处理令牌。更多令牌通​​常会导致更好的性能，但计算成本显着增加。通过谚语“一张图片胜过千言万语”，我们的目标是通过制造长图像短而加速VIT模型。为此，我们提出了一种新颖的方法在推论期间自适应地分配令牌长度。具体而言，我们首先培养一种含有可调整化 - vit（Revit）的Vit模型，可以处理任何具有不同令牌长度的给定输入。然后，我们从Revit检索“令牌长度标签”，并使用它培训轻量级令牌长度分配（TLA）。令牌长度标签是最小的令牌，以分割Revit可以使REVIT可以进行正确的预测，并且学习TLA以基于这些标签分配最佳令牌长度。 TLA使REVIT能够在推理期间使用最小足够数量的令牌处理图像。因此，通过减少VIT模型中的令牌数字来提高推广速度。我们的方法是一般的，与现代视觉变压器架构兼容，可以显着减少计算扩展。我们在两个任务中验证了我们对多个代表性VIT模型（DEIT，LV-VIT和TIMESFRER）的效果（图像分类和动作识别）。

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。

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.

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.

我们介绍了ADAVIT，一种可自适应地调整视觉变压器（VIT）推理成本的方法，用于不同复杂性的图像。 Adavit通过自动减少在网络中处理的视觉变压器中的令牌数量作为推理进行的令牌的数量来实现这一目标。我们为此任务进行重新格式化自适应计算时间（ACT），扩展为丢弃冗余空间令牌。视觉变换器的吸引力架构属性使我们的自适应令牌减少机制能够加速推理而不修改网络架构或推理硬件。我们展示了ADAVIT不需要额外的参数或子网来停止，因为我们基于自适应停止在原始网络参数上的学习。我们进一步引入了与现有行为方法相比稳定培训的分布先前正则化。在图像分类任务（ImageNet1K）上，我们表明我们提出的Adavit在过滤信息丰富的空间特征和削减整体计算上产生了高效率。所提出的方法将Deit-Tiny的吞吐量提高了62％并除去了38％，只有0.3％的精度下降，优于大边距。

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

Training large, deep neural networks to convergence can be prohibitively expensive. As a result, often only a small selection of popular, dense models are reused across different contexts and tasks. Increasingly, sparsely activated models, which seek to decouple model size from computation costs, are becoming an attractive alternative to dense models. Although more efficient in terms of quality and computation cost, sparse models remain data-hungry and costly to train from scratch in the large scale regime. In this work, we propose sparse upcycling -- a simple way to reuse sunk training costs by initializing a sparsely activated Mixture-of-Experts model from a dense checkpoint. We show that sparsely upcycled T5 Base, Large, and XL language models and Vision Transformer Base and Large models, respectively, significantly outperform their dense counterparts on SuperGLUE and ImageNet, using only ~50% of the initial dense pretraining sunk cost. The upcycled models also outperform sparse models trained from scratch on 100% of the initial dense pretraining computation budget.

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。

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。