mlsanityData to 7 Oct 2026

Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer

arXiv 2106.03650 ↗First posted 7 Jun 2021cs.CVcited by 115

Not on the map. Why?

Abstract (arXiv)

Very recently, Window-based Transformers, which computed self-attention within non-overlapping local windows, demonstrated promising results on image classification, semantic segmentation, and object detection. However, less study has been devoted to the cross-window connection which is the key element to improve the representation ability. In this work, we revisit the spatial shuffle as an efficient way to build connections among windows. As a result, we propose a new vision transformer, named Shuffle Transformer, which is highly efficient and easy to implement by modifying two lines of code. Furthermore, the depth-wise convolution is introduced to complement the spatial shuffle for enhancing neighbor-window connections. The proposed architectures achieve excellent performance on a wide range of visual tasks including image-level classification, object detection, and semantic segmentation. Code will be released for reproduction.

Key facts. Cited by 115 papers in the map (data through 7 Oct 2026). Builds on 43 of its 47 references that are in the map. First posted on arXiv 7 Jun 2021.

Builds on

43 of 47 references.

References · 43

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2017Mask R-CNNcited by 7,259
  8. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  9. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  10. 2016Layer Normalizationcited by 5,579
  11. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  12. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
31 more
  1. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  2. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  3. 2020Longformer: The Long-Document Transformercited by 3,362
  4. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  5. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  6. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  7. 2019Generating Long Sequences with Sparse Transformerscited by 1,523
  8. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  9. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  10. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,265
  11. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  12. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  13. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  14. 2020Designing Network Design Spacescited by 954
  15. 2021CvT: Introducing Convolutions to Vision Transformerscited by 946
  16. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  17. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 717
  18. 2021Transformer in Transformercited by 632
  19. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  20. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  21. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  22. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 494
  23. 2019GhostNet: More Features from Cheap Operationscited by 410
  24. 2021Conditional Positional Encodings for Vision Transformerscited by 402
  25. 2020Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentationcited by 326
  26. 2021Escaping the Big Data Paradigm with Compact Transformerscited by 261
  27. 2021LocalViT: Analyzing Locality in Vision Transformerscited by 228
  28. 2021Scaling Local Self-Attention for Parameter Efficient Visual Backbonescited by 220
  29. 2019Local Relation Networks for Image Recognitioncited by 210
  30. 2019Interlaced Sparse Self-Attention for Semantic Segmentationcited by 53
  31. 2020AlignSeg: Feature-Aligned Segmentation Networkscited by 53

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 41; 2023: 30; 2024: 15; 2025: 10; 2026: 3.

115 papers.

Sort:

By area:

  1. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  2. 2022Vision Transformer Adapter for Dense Predictionscited by 564
  3. 2022Activating More Pixels in Image Super-Resolution Transformercited by 433
  4. 2022Vision Transformers for Single Image Dehazingcited by 255
  5. 2022CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformerscited by 227
  6. 2022UniFormer: Unifying Convolution and Self-attention for Visual Recognitioncited by 206
  7. 2021Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformercited by 175
  8. 2022DaViT: Dual Attention Vision Transformerscited by 174
  9. 2021CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attentioncited by 139
  10. 2021CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptationcited by 129
  11. 2022Inception Transformercited by 99
  12. 2024ZigMa: A DiT-style Zigzag Mamba Diffusion Modelcited by 84
38 more
  1. 2022TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentationcited by 82
  2. 2022Fast Vision Transformers with HiLo Attentioncited by 78
  3. 2024ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictionscited by 65
  4. 2023HAT: Hybrid Attention Transformer for Image Restorationcited by 64
  5. 2021Are we ready for a new paradigm shift? A Survey on Visual Deep MLPcited by 63
  6. 2022CF-ViT: A General Coarse-to-Fine Method for Vision Transformercited by 63
  7. 2021On the Connection between Local Attention and Dynamic Depth-wise Convolutioncited by 61
  8. 2022Temporally Efficient Vision Transformer for Video Instance Segmentationcited by 55
  9. 2023Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanismcited by 51
  10. 2022Green Hierarchical Vision Transformer for Masked Image Modelingcited by 50
  11. 2023Scale-Aware Modulation Meet Transformercited by 49
  12. 2023Vision Transformer with Quadrangle Attentioncited by 46
  13. 2024A Survey on Transformer Compressioncited by 44
  14. 2022MixFormer: Mixing Features across Windows and Dimensionscited by 43
  15. 2022VSA: Learning Varied-Size Window Attention in Vision Transformerscited by 43
  16. 2022Vision Transformer with Super Token Samplingcited by 43
  17. 2023Image as Set of Pointscited by 43
  18. 2021Sparse MLP for Image Recognition: Is Self-Attention Really Necessary?cited by 38
  19. 2021ConvMLP: Hierarchical Convolutional MLPs for Visioncited by 37
  20. 2021Pale Transformer: A General Vision Transformer Backbone with Pale-Shaped Attentioncited by 36
  21. 2022ScalableViT: Rethinking the Context-oriented Generalization of Vision Transformercited by 36
  22. 2023DilateFormer: Multi-Scale Dilated Transformer for Visual Recognitioncited by 34
  23. 2023Visual Tuningcited by 34
  24. 2021Scaled ReLU Matters for Training Vision Transformerscited by 29
  25. 2023Making Vision Transformers Efficient from A Token Sparsification Viewcited by 28
  26. 2022EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithmcited by 27
  27. 2021S2-MLPv2: Improved Spatial-Shift MLP Architecture for Visioncited by 24
  28. 2022Fast-iTPN: Integrally Pre-Trained Transformer Pyramid Network with Token Migrationcited by 24
  29. 2023Point Cloud Classification Using Content-based Transformer via Clustering in Feature Spacecited by 19
  30. 2023Robustifying Token Attention for Vision Transformerscited by 19
  31. 2021ELSA: Enhanced Local Self-Attention for Vision Transformercited by 18
  32. 2023CrossFormer++: A Versatile Vision Transformer Hinging on Cross-scale Attentioncited by 18
  33. 2025RelaCtrl: Relevance-Guided Efficient Control for Diffusion Transformerscited by 18
  34. 2022SepViT: Separable Vision Transformercited by 16
  35. 2023UniNeXt: Exploring A Unified Architecture for Vision Recognitioncited by 16
  36. 2021Rethinking Token-Mixing MLP for MLP-based Vision Backbonecited by 15
  37. 2023Dual Cross-Attention for Medical Image Segmentationcited by 15
  38. 2023Universal Domain Adaptation via Compressive Attention Matchingcited by 15

50 most cited of 115 All 115 (JSON)