mlsanityData to 7 Oct 2026

Recent Advances in Vision Transformer: A Survey and Outlook of Recent Work

arXiv 2203.01536 ↗First posted 3 Mar 2022cs.CV cs.AIcited by 21

Not on the map. Why?

Abstract (arXiv)

Vision Transformers (ViTs) are becoming more popular and dominating technique for various vision tasks, compare to Convolutional Neural Networks (CNNs). As a demanding technique in computer vision, ViTs have been successfully solved various vision problems while focusing on long-range relationships. In this paper, we begin by introducing the fundamental concepts and background of the self-attention mechanism. Next, we provide a comprehensive overview of recent top-performing ViT methods describing in terms of strength and weakness, computational cost as well as training and testing dataset. We thoroughly compare the performance of various ViT algorithms and most representative CNN methods on popular benchmark datasets. Finally, we explore some limitations with insightful observations and provide further research direction. The project page along with the collections of papers are available at https://github.com/khawar512/ViT-Survey

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 56 of its 61 references that are in the map. First posted on arXiv 3 Mar 2022.

Builds on

56 of 61 references.

References · 56

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  6. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  7. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,552
  8. 2020Point Transformercited by 1,462
  9. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  10. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,218
  11. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  12. 2021UNETR: Transformers for 3D Medical Image Segmentationcited by 954
38 more
  1. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 864
  2. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  3. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  4. 2021Going deeper with Image Transformerscited by 759
  5. 2021TransReID: Transformer-based Object Re-Identificationcited by 432
  6. 2021Transformer Trackingcited by 412
  7. 2021Medical Transformer: Gated Axial-Attention for Medical Image Segmentationcited by 319
  8. 2021DeepViT: Towards Deeper Vision Transformercited by 288
  9. 2021LocalViT: Analyzing Locality in Vision Transformerscited by 228
  10. 2022VRT: A Video Restoration Transformercited by 219
  11. 2021Rethinking and Improving Relative Position Encoding for Vision Transformercited by 206
  12. 20203D Object Detection with Pointformercited by 194
  13. 2021SSAST: Self-Supervised Audio Spectrogram Transformercited by 166
  14. 2021VOLO: Vision Outlooker for Visual Recognitioncited by 164
  15. 2021StyleSwin: Transformer-based GAN for High-resolution Image Generationcited by 152
  16. 2022Multiview Transformers for Video Recognitioncited by 148
  17. 2021TransFG: A Transformer Architecture for Fine-grained Recognitioncited by 131
  18. 2021Transformer-Based Attention Networks for Continuous Pixel-Wise Predictioncited by 125
  19. 2021Generative Adversarial Transformerscited by 120
  20. 2021Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformercited by 119
  21. 2021UTNet: A Hybrid Transformer Architecture for Medical Image Segmentationcited by 116
  22. 2021DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformercited by 111
  23. 2021Fast Point Transformercited by 103
  24. 2021Combining EfficientNet and Vision Transformers for Video Deepfake Detectioncited by 81
  25. 2021Medical Image Segmentation Using Squeeze-and-Expansion Transformerscited by 56
  26. 2021VTNet: Visual Transformer Network for Object Goal Navigationcited by 50
  27. 2021AAformer: Auto-Aligned Transformer for Person Re-Identificationcited by 48
  28. 2021Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identificationcited by 44
  29. 2021Trear: Transformer-based RGB-D Egocentric Action Recognitioncited by 39
  30. 2021HAT: Hierarchical Aggregation Transformers for Person Re-identificationcited by 39
  31. 2021SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognitioncited by 36
  32. 2021CCTrans: Simplifying and Improving Crowd Counting with Transformercited by 30
  33. 2021A Video Is Worth Three Views: Trigeminal Transformers for Video-based Person Re-identificationcited by 28
  34. 2021Dual Transformer for Point Cloud Analysiscited by 26
  35. 2021Towards End-to-End Image Compression and Analysis with Transformerscited by 26
  36. 2021Fully Transformer Networks for Semantic Image Segmentationcited by 24
  37. 2021Generative Video Transformer: Can Objects be the Words?cited by 24
  38. 2021SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimationcited by 23

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 9; 2024: 7; 2025: 2; 2026: 1.

21 papers.

Sort:

By area:

  1. 2023E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuningcited by 70
  2. 2023Rethinking Mobile Block for Efficient Attention-based Modelscited by 36
  3. 2023FT2TF: First-Person Statement Text-To-Talking Face Generationcited by 26
  4. 2023A Recent Survey of Vision Transformers for Medical Image Segmentationcited by 22
  5. 2024GenMix: Effective Data Augmentation with Generative Diffusion Model Image Editingcited by 14
  6. 2023Occluded Person Re-Identification with Deep Learning: A Survey and Perspectivescited by 13
  7. 2024AMD: Automatic Multi-step Distillation of Large-scale Vision Modelscited by 12
  8. 2023Transformers in Single Object Tracking: An Experimental Surveycited by 10
  9. 2023Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformerscited by 9
  10. 2023SAIC: Integration of Speech Anonymization and Identity Classificationcited by 7
  11. 2024EMOv2: Pushing 5M Vision Model Frontiercited by 5
  12. 2025Generative Pre-training for Subjective Tasks: A Diffusion Transformer-Based Framework for Facial Beauty Predictioncited by 4
9 more
  1. 2024Foundation Models for Autonomous Robots in Unstructured Environmentscited by 3
  2. 2023SkyGPT: Probabilistic Short-term Solar Forecasting Using Synthetic Sky Videos from Physics-constrained VideoGPTcited by 2
  3. 2024OCT-SelfNet: A Self-Supervised Framework with Multi-Modal Datasets for Generalized and Robust Retinal Disease Detectioncited by 2
  4. 2024Multi-OCT-SelfNet: Integrating Self-Supervised Learning with Multi-Source Data Fusion for Enhanced Multi-Class Retinal Disease Classificationcited by 1
  5. 2022Sequence and Circle: Exploring the Relationship Between Patchescited by 0
  6. 2022RevealED: Uncovering Pro-Eating Disorder Content on Twitter Using Deep Learningcited by 0
  7. 2024Towards In-Vehicle Multi-Task Facial Attribute Recognition: Investigating Synthetic Data and Vision Foundation Modelscited by 0
  8. 2025Towards Foundation Models for Cryo-ET Subtomogram Analysiscited by 0
  9. 2026Hierarchical Reinforcement Learning for Neural Network Compression (HiReLC): Pruning and Quantizationcited by 0