We introduce dense vision transformers, an architecture that leverages vision transformers in place of convolutional networks as a backbone for dense prediction tasks. We assemble tokens from various stages of the vision transformer into image-like representations at various resolutions and progressively combine them into full-resolution predictions using a convolutional decoder. The transformer backbone processes representations at a constant and relatively high resolution and has a global receptive field at every stage. These properties allow the dense vision transformer to provide finer-grained and more globally coherent predictions when compared to fully-convolutional networks. Our experiments show that this architecture yields substantial improvements on dense prediction tasks, especially when a large amount of training data is available. For monocular depth estimation, we observe an improvement of up to 28% in relative performance when compared to a state-of-theart fully-convolutional network. When applied to semantic segmentation, dense vision transformers set a new state of the art on ADE20K with 49.02% mIoU. We further show that the architecture can be fine-tuned on smaller datasets such as NYUv2, KITTI, and Pascal Context where it also sets the new state of the art. Our models are available at https://github.com/intel-isl/DPT.

由于长距离依赖性建模的能力，变压器在各种自然语言处理和计算机视觉任务中表现出令人印象深刻的性能。最近的进展证明，将这种变压器与基于CNN的语义图像分割模型相结合非常有前途。然而，目前还没有很好地研究了纯变压器的方法如何实现图像分割。在这项工作中，我们探索了语义图像分割的新框架，它是基于编码器 - 解码器的完全变压器网络（FTN）。具体地，我们首先提出金字塔组变压器（PGT）作为逐步学习分层特征的编码器，同时降低标准视觉变压器（VIT）的计算复杂性。然后，我们将特征金字塔变换器（FPT）提出了来自PGT编码器的多电平进行语义图像分割的多级别的语义级别和空间级信息。令人惊讶的是，这种简单的基线可以在多个具有挑战性的语义细分和面部解析基准上实现更好的结果，包括帕斯卡背景，ADE20K，Cocostuff和Celebamask-HQ。源代码将在https://github.com/br -dl/paddlevit上发布。

Image segmentation is often ambiguous at the level of individual image patches and requires contextual information to reach label consensus. In this paper we introduce Segmenter, a transformer model for semantic segmentation. In contrast to convolution-based methods, our approach allows to model global context already at the first layer and throughout the network. We build on the recent Vision Transformer (ViT) and extend it to semantic segmentation. To do so, we rely on the output embeddings corresponding to image patches and obtain class labels from these embeddings with a point-wise linear decoder or a mask transformer decoder. We leverage models pre-trained for image classification and show that we can fine-tune them on moderate sized datasets available for semantic segmentation. The linear decoder allows to obtain excellent results already, but the performance can be further improved by a mask transformer generating class masks. We conduct an extensive ablation study to show the impact of the different parameters, in particular the performance is better for large models and small patch sizes. Segmenter attains excellent results for semantic segmentation. It outperforms the state of the art on both ADE20K and Pascal Context datasets and is competitive on Cityscapes.

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。

Most recent semantic segmentation methods adopt a fully-convolutional network (FCN) with an encoderdecoder architecture. The encoder progressively reduces the spatial resolution and learns more abstract/semantic visual concepts with larger receptive fields. Since context modeling is critical for segmentation, the latest efforts have been focused on increasing the receptive field, through either dilated/atrous convolutions or inserting attention modules. However, the encoder-decoder based FCN architecture remains unchanged. In this paper, we aim to provide an alternative perspective by treating semantic segmentation as a sequence-to-sequence prediction task. Specifically, we deploy a pure transformer (i.e., without convolution and resolution reduction) to encode an image as a sequence of patches. With the global context modeled in every layer of the transformer, this encoder can be combined with a simple decoder to provide a powerful segmentation model, termed SEgmentation TRansformer (SETR). Extensive experiments show that SETR achieves new state of the art on ADE20K (50.28% mIoU), Pascal Context (55.83% mIoU) and competitive results on Cityscapes. Particularly, we achieve the first position in the highly competitive ADE20K test server leaderboard on the day of submission.

Recently, transformer networks have outperformed traditional deep neural networks in natural language processing and show a large potential in many computer vision tasks compared to convolutional backbones. In the original transformer, readout tokens are used as designated vectors for aggregating information from other tokens. However, the performance of using readout tokens in a vision transformer is limited. Therefore, we propose a novel fusion strategy to integrate radar data into a dense prediction transformer network by reassembling camera representations with radar representations. Instead of using readout tokens, radar representations contribute additional depth information to a monocular depth estimation model and improve performance. We further investigate different fusion approaches that are commonly used for integrating additional modality in a dense prediction transformer network. The experiments are conducted on the nuScenes dataset, which includes camera images, lidar, and radar data. The results show that our proposed method yields better performance than the commonly used fusion strategies and outperforms existing convolutional depth estimation models that fuse camera images and radar.

ous vision tasks without convolutions, where it can be used as a direct replacement for CNN backbones. (3) We validate PVT through extensive experiments, showing that it boosts the performance of many downstream tasks, including object detection, instance and semantic segmentation. For example, with a comparable number of parameters, PVT+RetinaNet achieves 40.4 AP on the COCO dataset, surpassing ResNet50+RetinNet (36.3 AP) by 4.1 absolute AP (see Figure 2). We hope that PVT could serve as an alternative and useful backbone for pixel-level predictions and facilitate future research.

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

这项工作介绍了一个简单的视觉变压器设计，作为对象本地化和实例分段任务的强大基线。变压器最近在图像分类任务中展示了竞争性能。为了采用对象检测和密集的预测任务，许多作品从卷积网络和高度定制的Vit架构继承了多级设计。在这种设计背后，目标是在计算成本和多尺度全球背景的有效聚合之间进行更好的权衡。然而，现有的作品采用多级架构设计作为黑匣子解决方案，无清楚地了解其真正的益处。在本文中，我们全面研究了三个架构设计选择对vit - 空间减少，加倍的频道和多尺度特征 - 并证明了vanilla vit架构可以在没有手动的多尺度特征的情况下实现这一目标，保持原始的Vit设计哲学。我们进一步完成了缩放规则，以优化模型的准确性和计算成本/型号大小的权衡。通过在整个编码器块中利用恒定的特征分辨率和隐藏大小，我们提出了一种称为通用视觉变压器（UVIT）的简单而紧凑的VIT架构，可实现COCO对象检测和实例分段任务的强劲性能。

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.

We explore the capability of plain Vision Transformers (ViTs) for semantic segmentation and propose the SegVit. Previous ViT-based segmentation networks usually learn a pixel-level representation from the output of the ViT. Differently, we make use of the fundamental component -- attention mechanism, to generate masks for semantic segmentation. Specifically, we propose the Attention-to-Mask (ATM) module, in which the similarity maps between a set of learnable class tokens and the spatial feature maps are transferred to the segmentation masks. Experiments show that our proposed SegVit using the ATM module outperforms its counterparts using the plain ViT backbone on the ADE20K dataset and achieves new state-of-the-art performance on COCO-Stuff-10K and PASCAL-Context datasets. Furthermore, to reduce the computational cost of the ViT backbone, we propose query-based down-sampling (QD) and query-based up-sampling (QU) to build a Shrunk structure. With the proposed Shrunk structure, the model can save up to $40\%$ computations while maintaining competitive performance.

多任务密集的场景理解是一个蓬勃发展的研究领域，需要同时对与像素预测的一系列相关任务进行推理。由于卷积操作的大量利用，大多数现有作品都会遇到当地建模的严重限制，而在全球空间位置和多任务背景中学习相互作用和推断对于此问题至关重要。在本文中，我们提出了一种新颖的端到端倒立金字塔多任务变压器（Invpt），以在统一框架中对空间位置和多个任务进行同时建模。据我们所知，这是探索设计变压器结构的第一项工作，以用于多任务密集的预测以进行场景理解。此外，人们广泛证明，较高的空间分辨率对密集的预测非常有益，而对于现有的变压器来说，由于对大空间大小的巨大复杂性，现有变形金刚更深入地采用更高的分辨率。 Invpt提出了一个有效的上移动器块，以逐渐增加分辨率学习多任务特征交互，这还结合了有效的自我发言消息传递和多规模特征聚合，以高分辨率产生特定于任务的预测。我们的方法分别在NYUD-V2和PASCAL-CONTEXT数据集上实现了卓越的多任务性能，并且显着优于先前的最先前。该代码可在https://github.com/prismformore/invpt上获得

We present SegFormer, a simple, efficient yet powerful semantic segmentation framework which unifies Transformers with lightweight multilayer perceptron (MLP) decoders. SegFormer has two appealing features: 1) SegFormer comprises a novel hierarchically structured Transformer encoder which outputs multiscale features. It does not need positional encoding, thereby avoiding the interpolation of positional codes which leads to decreased performance when the testing resolution differs from training. 2) SegFormer avoids complex decoders. The proposed MLP decoder aggregates information from different layers, and thus combining both local attention and global attention to render powerful representations. We show that this simple and lightweight design is the key to efficient segmentation on Transformers. We scale our approach up to obtain a series of models from SegFormer-B0 to SegFormer-B5, reaching significantly better performance and efficiency than previous counterparts. For example, SegFormer-B4 achieves 50.3% mIoU on ADE20K with 64M parameters, being 5× smaller and 2.2% better than the previous best method. Our best model, SegFormer-B5, achieves 84.0% mIoU on Cityscapes validation set and shows excellent zero-shot robustness on Cityscapes-C. Code will be released at: github.com/NVlabs/SegFormer.Preprint. Under review.

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。

图像中的场景细分是视觉内容理解中的一个基本而又具有挑战性的问题，即学习一个模型，将每个图像像素分配给分类标签。这项学习任务的挑战之一是考虑空间和语义关系以获得描述性特征表示，因此从多个量表中学习特征图是场景细分中的一种常见实践。在本文中，我们探讨了在多尺度图像窗口中自我发挥的有效使用来学习描述性视觉特征，然后提出三种不同的策略来汇总这些特征图以解码特征表示形式以进行密集的预测。我们的设计基于最近提出的SWIN Transformer模型，该模型完全放弃了卷积操作。借助简单而有效的多尺度功能学习和聚合，我们的模型在四个公共场景细分数据集，Pascal VOC2012，Coco-STUFF 10K，ADE20K和CITYSCAPES上实现了非常有希望的性能。

The recently developed vision transformer (ViT) has achieved promising results on image classification compared to convolutional neural networks. Inspired by this, in this paper, we study how to learn multi-scale feature representations in transformer models for image classification. To this end, we propose a dual-branch transformer to combine image patches (i.e., tokens in a transformer) of different sizes to produce stronger image features. Our approach processes small-patch and large-patch tokens with two separate branches of different computational complexity and these tokens are then fused purely by attention multiple times to complement each other. Furthermore, to reduce computation, we develop a simple yet effective token fusion module based on cross attention, which uses a single token for each branch as a query to exchange information with other branches. Our proposed cross-attention only requires linear time for both computational and memory complexity instead of quadratic time otherwise. Extensive experiments demonstrate that our approach performs better than or on par with several concurrent works on vision transformer, in addition to efficient CNN models. For example, on the ImageNet1K dataset, with some architectural changes, our approach outperforms the recent DeiT by a large margin of 2% with a small to moderate increase in FLOPs and model parameters. Our source codes and models are available at https://github.com/IBM/CrossViT.

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。

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。

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.

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.