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 \textbf{S}hifted \textbf{win}dows. 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 test-dev) and semantic segmentation (53.5 mIoU on ADE20K val). Its performance surpasses the previous state-of-the-art 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~\url{https://github.com/microsoft/Swin-Transformer}.
Rethinking Surgical Captioning: End-to-End Window-Based MLP Transformer Using Patches
The Chinese University of Hong Kong（香港中文大学）；National University of Singapore（新加坡国立大学）；Imperial College London（帝国理工学院）；National University of Singapore (Suzhou) Research Institute（新加坡国立大学（苏州）研究院）
SwinMamba: A hybrid local-global mamba framework for enhancing semantic segmentation of remotely sensed images
Xi'an Jiaotong-Liverpool University（西交利物浦大学）；University of Liverpool（利物浦大学）；Nanyang Technological University（南洋理工大学）；SJTUSME-COSMOPlat Joint Research Center for New Generation Industrial Intelligent Technology（上海交通大学机械与动力工程学院-卡奥斯新一代工业智能技术联合研究中心）
MSW-Transformer: Multi-Scale Shifted Windows Transformer Networks for 12-Lead ECG Classification
Shantou University（汕头大学）；Sun Yet-sun University（中山大学）；The First Affiliated Hospital of Shantou University（汕头大学第一附属医院）；Shantou Institute of Ultrasonic Instruments Co., Ltd.（汕头超声仪器研究所有限公司）
Spatio-Temporal Hybrid Fusion of CAE and SWIn Transformers for Lung Cancer Malignancy Prediction
Concordia University（康考迪亚大学）；Concordia Institute for Information Systems Engineering（康考迪亚信息系统工程研究所）；Sunnybrook Health Sciences Centre（桑尼布鲁克健康科学中心）；University of Toronto（多伦多大学）
Swin Deformable Attention U-Net Transformer (SDAUT) for Explainable Fast MRI
National Heart and Lung Institute, Imperial College London（帝国理工学院国家心肺研究所）；Cardiovascular Research Centre, Royal Brompton Hospital（皇家布朗普顿医院心血管研究中心）；School of Biomedical Engineering, Sun Yat-sen University（中山大学生物医学工程学院）
Multi-branch Cascaded Swin Transformers with Attention to k-space Sampling Pattern for Accelerated MRI Reconstruction
Monash Biomedical Imaging, Monash University（莫纳什大学生物医学成像中心）；Department of Electrical and Computer Systems Engineering, Monash University（莫纳什大学电气与计算机系统工程系）；School of Psychological Sciences, Monash University（莫纳什大学心理科学学院）；Department of Data Science and AI, Monash University（莫纳什大学数据科学与人工智能系）
SwinECAT: A Transformer-based fundus disease classification model with Shifted Window Attention and Efficient Channel Attention
School of Physics and Information Technology（物理与信息学院）；Shaanxi Normal University（陕西师范大学）；School of Computer Science and Engineering（计算机科学与工程学院）；Central South University（中南大学）
FLASHSWIN: Unlocking Large Windows and Dense Tokens in Swin Vision Transformers with Memory Efficient Attention
Scientific Computing and Imaging Institute, University of Utah（犹他大学科学计算与影像研究所）；Kahlert School of Computing, University of Utah（犹他大学卡勒特计算学院）；RNET Technologies（RNET技术公司）
AS-MLP: An Axial Shifted MLP Architecture for Vision
ShanghaiTech University（上海科技大学）；Tencent（腾讯）；Shanghai Engineering Research Center of Intelligent Vision and Imaging（上海智能视觉与成像工程研究中心）；Shanghai Engineering Research Center of Energy Efficient and Custom AI IC（上海高效节能与定制AI芯片工程研究中心）
提出了一种轴向移位的MLP结构（AS-MLP）。与MLP混合器通过矩阵转置和单标记混合MLP对全局空间特征进行信息流编码不同，我们更关注局部特征的交互。通过轴向移动特征映射的通道，AS-MLP能够从不同的轴向方向获得信息流，从而捕获局部依赖性。这样的操作使我们能够利用纯MLP架构来实现与CNN类架构相同的局部感受野。我们还可以设计AS-MLP的感受野大小和块的膨胀等，在卷积神经网络的相同精神。使用所提出的AS-MLP架构，我们的模型在ImageNet-1 K数据集上获得了83.3%的Top-1准确率，88 M参数和15.2 GFLOPs。这种简单而有效的架构优于所有基于MLP的架构，并且与基于变压器的架构（例如，Swin Transformer），即使FLOPs略低。此外，AS-MLP也是第一个应用于下游任务（例如，目标检测和语义分割）。实验结果也令人印象深刻。我们提出的AS-MLP在COCO验证集上获得51.5 mAP，在ADE 20 K数据集上获得49.5 MS mIoU，与基于transformer的架构相比具有竞争力。我们的AS-MLP建立了一个强大的基于MLP的架构基线。代码可在https://github.com/svip-lab/AS-MLP上获得。
HRFormer: High-Resolution Transformer for Dense Prediction
Peking University（北京大学）；Microsoft Research Asia（微软亚洲研究院）；Baidu（百度）；University of Chinese Academy of Sciences（中国科学院大学）；Institute of Computing Technology, CAS（中国科学院计算技术研究所）
我们提出了一个高分辨率的Transformer（HRFormer），学习高分辨率表示密集的预测任务，与原始的视觉Transformer，产生低分辨率的表示，并具有较高的内存和计算成本。我们利用高分辨率卷积网络（HRNet）中引入的多分辨率并行设计，以及在小的非重叠图像窗口上执行自注意的局部窗口自注意，以提高内存和计算效率。此外，我们将卷积引入到FFN中，以跨断开的图像窗口交换信息。我们证明了高分辨率Transformer在人体姿势估计和语义分割任务上的有效性，例如，HRFormer在COCO姿态估计方面优于Swin Transformer by $1.3$ AP，具有更少的参数和更少的FLOP，其中$50\%$和$30\%$更少。代码可在：https://github.com/HRNet/HRFormer.
Chalmers University of Technology（查尔姆斯理工大学）；University of Gothenburg（哥德堡大学）；Technical University Berlin（柏林工业大学）；Umeå University（于默奥大学）；Zenseact（森赛克特公司）
CLFTv2: Efficient Camera-LiDAR Fusion for Semantic Segmentation via Hierarchical Feature Pyramids
Tallinn University of Technology（塔林理工大学）；FinEst Centre for Smart Cities, Tallinn University of Technology（塔林理工大学芬埃斯特智慧城市中心）；Universitas Mercatorum（梅尔卡托鲁姆大学）
AgileIR: Memory-Efficient Group Shifted Windows Attention for Agile Image Restoration
Faculty of Computer Science；Information Technology University of Malaya Kuala Lumpur, Malaysia；School of Intelligence Science；Technology University of Science；Faculty of Art；Design Fuzhou University of International Studies
Imperial College London（帝国理工学院）；Royal Brompton Hospital（皇家布朗普顿医院）；Sun Yat-sen University（中山大学）；Beihang University（北京航空航天大学）；University of the Basque Country UPV/EHU（巴斯克大学（UPV/EHU））；TECNALIA（泰克纳利亚研究中心）；Shenzhen Second People’s Hospital（深圳市第二人民医院）；The First Affiliated Hospital of Shenzhen University Health Science Center（深圳大学医学部第一附属医院）
SKGE-SWIN: End-To-End Autonomous Vehicle Waypoint Prediction and Navigation Using Skip Stage Swin Transformer
Department of Computer Science, Indonesia University of Education（印度尼西亚教育大学计算机科学系）；Research Center for Smart Mechatronics, National Research and Innovation Agency（国家研究与创新局智能机电研究中心）；Department of Computer Science and Electronics, Gadjah Mada University（加查玛达大学计算机科学与电子系）
