mlsanityData to 14 Oct 2026

A Comprehensive Survey of Transformers for Computer Vision

arXiv 2211.06004 ↗First posted 11 Nov 2022cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

As a special type of transformer, Vision Transformers (ViTs) are used to various computer vision applications (CV), such as image recognition. There are several potential problems with convolutional neural networks (CNNs) that can be solved with ViTs. For image coding tasks like compression, super-resolution, segmentation, and denoising, different variants of the ViTs are used. The purpose of this survey is to present the first application of ViTs in CV. The survey is the first of its kind on ViTs for CVs to the best of our knowledge. In the first step, we classify different CV applications where ViTs are applicable. CV applications include image classification, object detection, image segmentation, image compression, image super-resolution, image denoising, and anomaly detection. Our next step is to review the state-of-the-art in each category and list the available models. Following that, we present a detailed analysis and comparison of each model and list its pros and cons. After that, we present our insights and lessons learned for each category. Moreover, we discuss several open research challenges and future research directions.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 50 of its 71 references that are in the map. First posted on arXiv 11 Nov 2022.

Builds on

50 of 71 references.

References · 50

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  7. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  8. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  9. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  10. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  11. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,620
  12. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,558
38 more
  1. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,200
  2. 2016Modeling Context in Referring Expressionscited by 1,063
  3. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,060
  4. 2019BERT Rediscovers the Classical NLP Pipelinecited by 1,059
  5. 2021Transformers in Vision: A Surveycited by 1,013
  6. 2021CvT: Introducing Convolutions to Vision Transformerscited by 947
  7. 2018Variational image compression with a scale hyperpriorcited by 935
  8. 2015Generation and Comprehension of Unambiguous Object Descriptionscited by 904
  9. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  10. 2020Efficient Transformers: A Surveycited by 790
  11. 2021Do Vision Transformers See Like Convolutional Neural Networks?cited by 675
  12. 2021The Medical Segmentation Decathloncited by 628
  13. 2021CoAtNet: Marrying Convolution and Attention for All Data Sizescited by 569
  14. 2021The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classificationcited by 518
  15. 2021Intriguing Properties of Vision Transformerscited by 446
  16. 2021A Survey of Transformerscited by 401
  17. 2021Early Convolutions Help Transformers See Bettercited by 396
  18. 2021Rethinking Spatial Dimensions of Vision Transformerscited by 361
  19. 2021LAVT: Language-Aware Vision Transformer for Referring Image Segmentationcited by 348
  20. 2020Visual Transformers: Token-based Image Representation and Processing for Computer Visioncited by 334
  21. 2016Modeling Context Between Objects for Referring Expression Understandingcited by 251
  22. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 223
  23. 2021Group-Free 3D Object Detection via Transformerscited by 215
  24. 2016Wider or Deeper: Revisiting the ResNet Model for Visual Recognitioncited by 184
  25. 2021You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detectioncited by 170
  26. 2021Benchmarking Detection Transfer Learning with Vision Transformerscited by 131
  27. 2021A Survey of Visual Transformerscited by 117
  28. 2022Entroformer: A Transformer-based Entropy Model for Learned Image Compressioncited by 107
  29. 2020Toward Transformer-Based Object Detectioncited by 84
  30. 2021Combining EfficientNet and Vision Transformers for Video Deepfake Detectioncited by 82
  31. 2022AnoViT: Unsupervised Anomaly Detection and Localization with Vision Transformer-based Encoder-Decodercited by 29
  32. 2021TED-net: Convolution-free T2T Vision Transformer-based Encoder-decoder Dilation network for Low-dose CT Denoisingcited by 21
  33. 2022Bridged Transformer for Vision and Point Cloud 3D Object Detectioncited by 20
  34. 2021Manipulation Detection in Satellite Images Using Vision Transformercited by 16
  35. 2022UNetFormer: A Unified Vision Transformer Model and Pre-Training Framework for 3D Medical Image Segmentationcited by 16
  36. 2021Vision Transformer for femur fracture classificationcited by 5
  37. 2022ViTBIS: Vision Transformer for Biomedical Image Segmentationcited by 5
  38. 2022Spatio-temporal Vision Transformer for Super-resolution Microscopycited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 0; 2024: 5; 2025: 6; 2026: 2.

14 papers.

Sort:

By area:

  1. 2024UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecastingcited by 13
  2. 2025Optimal Control for Transformer Architectures: Enhancing Generalization, Robustness and Efficiencycited by 8
  3. 2025CENet: Context Enhancement Network for Medical Image Segmentationcited by 5
  4. 2024Convolutional Neural Networks and Vision Transformers for Fashion MNIST Classification: A Literature Reviewcited by 2
  5. 2024Text Classification: Neural Networks VS Machine Learning Models VS Pre-trained Modelscited by 2
  6. 2025Artificial Intelligence for Direct Prediction of Molecular Dynamics Across Chemical Spacecited by 2
  7. 2022Fingerprint Pore Detection: A Surveycited by 0
  8. 2024Survey: Transformer-based Models in Data Modality Conversioncited by 0
  9. 2024COMFORT: A Continual Fine-Tuning Framework for Foundation Models Targeted at Consumer Healthcarecited by 0
  10. 2025A Comparison Between Decision Transformers and Traditional Offline Reinforcement Learning Algorithmscited by 0
  11. 2025Transformers for Tabular Data: A Training Perspective of Self-Attention via Optimal Transportcited by 0
  12. 2025MotivNet: Evolving Meta-Sapiens into an Emotionally Intelligent Foundation Modelcited by 0
2 more
  1. 2026Scaling Vision Transformers: Evaluating DeepSpeed for Image-Centric Workloadscited by 0
  2. 2026Design Choices for Multimodal Transformer Learning with Missing and Longitudinal Healthcare Datacited by 0