mlsanityData to 7 Oct 2026

MaxViT: Multi-Axis Vision Transformer

arXiv 2204.01697 ↗First posted 4 Apr 2022cs.CV cs.AI cs.LGcited by 476

Not on the map. Why?

Abstract (arXiv)

Transformers have recently gained significant attention in the computer vision community. However, the lack of scalability of self-attention mechanisms with respect to image size has limited their wide adoption in state-of-the-art vision backbones. In this paper we introduce an efficient and scalable attention model we call multi-axis attention, which consists of two aspects: blocked local and dilated global attention. These design choices allow global-local spatial interactions on arbitrary input resolutions with only linear complexity. We also present a new architectural element by effectively blending our proposed attention model with convolutions, and accordingly propose a simple hierarchical vision backbone, dubbed MaxViT, by simply repeating the basic building block over multiple stages. Notably, MaxViT is able to ''see'' globally throughout the entire network, even in earlier, high-resolution stages. We demonstrate the effectiveness of our model on a broad spectrum of vision tasks. On image classification, MaxViT achieves state-of-the-art performance under various settings: without extra data, MaxViT attains 86.5% ImageNet-1K top-1 accuracy; with ImageNet-21K pre-training, our model achieves 88.7% top-1 accuracy. For downstream tasks, MaxViT as a backbone delivers favorable performance on object detection as well as visual aesthetic assessment. We also show that our proposed model expresses strong generative modeling capability on ImageNet, demonstrating the superior potential of MaxViT blocks as a universal vision module. The source code and trained models will be available at https://github.com/google-research/maxvit.

Key facts. Cited by 476 papers in the map (data through 7 Oct 2026). Builds on 98 of its 112 references that are in the map. First posted on arXiv 4 Apr 2022.

Builds on

98 of 112 references.

References · 98

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  5. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  6. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  7. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  8. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  9. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  10. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  11. 2020End-to-End Object Detection with Transformerscited by 7,384
  12. 2017Mask R-CNNcited by 7,259
38 more
  1. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  2. 2016Densely Connected Convolutional Networkscited by 6,691
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  4. 2022Generative Adversarial Networkscited by 5,603
  5. 2016Layer Normalizationcited by 5,579
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  7. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  9. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  10. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  11. 2017Squeeze-and-Excitation Networkscited by 4,763
  12. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  13. 2014Going Deeper with Convolutionscited by 4,231
  14. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  15. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  16. 2022A ConvNet for the 2020scited by 3,545
  17. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  18. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  19. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  20. 2016Improved Techniques for Training GANscited by 2,938
  21. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
  22. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  23. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  24. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  25. 2017Non-local Neural Networkscited by 2,290
  26. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  27. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  28. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  29. 2021ViViT: A Video Vision Transformercited by 1,610
  30. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  31. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  32. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,199
  33. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,127
  34. 2018Self-Attention with Relative Position Representationscited by 1,112
  35. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  36. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
  37. 2021Transformers in Vision: A Surveycited by 1,009
  38. 2021Scaling Vision Transformerscited by 993

50 most cited of 98 All 98 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 45; 2023: 130; 2024: 122; 2025: 116; 2026: 63.

476 papers.

Sort:

By area:

  1. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 703
  2. 2022EVA: Exploring the Limits of Masked Visual Representation Learning at Scalecited by 685
  3. 2022Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Taskscited by 510
  4. 2023VideoPoet: A Large Language Model for Zero-Shot Video Generationcited by 479
  5. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 422
  6. 2023Hyena Hierarchy: Towards Larger Convolutional Language Modelscited by 388
  7. 2023SVDiff: Compact Parameter Space for Diffusion Fine-Tuningcited by 338
  8. 2022EfficientFormer: Vision Transformers at MobileNet Speedcited by 240
  9. 2022CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformerscited by 227
  10. 2024MambaVision: A Hybrid Mamba-Transformer Vision Backbonecited by 222
  11. 2023SCLIP: Rethinking Self-Attention for Dense Vision-Language Inferencecited by 169
  12. 2022Recurrent Video Restoration Transformer with Guided Deformable Attentioncited by 168
38 more
  1. 2023FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterizationcited by 161
  2. 2022Recurrent Vision Transformers for Object Detection with Event Camerascited by 158
  3. 2022Multi-Agent Reinforcement Learning is a Sequence Modeling Problemcited by 153
  4. 2023BiFormer: Vision Transformer with Bi-Level Routing Attentioncited by 150
  5. 2024EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mambacited by 146
  6. 2022More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsitycited by 142
  7. 2024MambaOut: Do We Really Need Mamba for Vision?cited by 142
  8. 2022MetaFormer Baselines for Visioncited by 131
  9. 2023Dual Aggregation Transformer for Image Super-Resolutioncited by 124
  10. 2022Rethinking Vision Transformers for MobileNet Size and Speedcited by 121
  11. 2023Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understandingcited by 111
  12. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 105
  13. 2022HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutionscited by 103
  14. 2024Logit Standardization in Knowledge Distillationcited by 101
  15. 2022Inception Transformercited by 99
  16. 2022Global Context Vision Transformerscited by 98
  17. 2022Brain Network Transformercited by 92
  18. 2023Leaving Reality to Imagination: Robust Classification via Generated Datasetscited by 91
  19. 2022E-Branchformer: Branchformer with Enhanced merging for speech recognitioncited by 90
  20. 2023Rethinking Model Ensemble in Transfer-based Adversarial Attackscited by 88
  21. 2023LDMVFI: Video Frame Interpolation with Latent Diffusion Modelscited by 88
  22. 2022Position: Considerations for Differentially Private Learning with Large-Scale Public Pretrainingcited by 86
  23. 2022Accurate Image Restoration with Attention Retractable Transformercited by 85
  24. 2023MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazingcited by 81
  25. 2024SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time seriescited by 81
  26. 2023Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Modelscited by 79
  27. 2023Generating images of rare concepts using pre-trained diffusion modelscited by 78
  28. 2023HM-ViT: Hetero-modal Vehicle-to-Vehicle Cooperative perception with vision transformercited by 70
  29. 2023Deep Learning for Day Forecasts from Sparse Observationscited by 70
  30. 2023RMT: Retentive Networks Meet Vision Transformerscited by 68
  31. 2023SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applicationscited by 66
  32. 2023FasterViT: Fast Vision Transformers with Hierarchical Attentioncited by 65
  33. 2022Dilated Neighborhood Attention Transformercited by 64
  34. 2024EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentationcited by 64
  35. 2023VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretrainingcited by 63
  36. 2024Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challengescited by 63
  37. 2024Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Modelcited by 62
  38. 2023TransNeXt: Robust Foveal Visual Perception for Vision Transformerscited by 61

50 most cited of 476 All 476 (JSON)