mlsanityData to 7 Oct 2026

Transformers Meet Visual Learning Understanding: A Comprehensive Review

arXiv 2203.12944 ↗First posted 24 Mar 2022cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Dynamic attention mechanism and global modeling ability make Transformer show strong feature learning ability. In recent years, Transformer has become comparable to CNNs methods in computer vision. This review mainly investigates the current research progress of Transformer in image and video applications, which makes a comprehensive overview of Transformer in visual learning understanding. First, the attention mechanism is reviewed, which plays an essential part in Transformer. And then, the visual Transformer model and the principle of each module are introduced. Thirdly, the existing Transformer-based models are investigated, and their performance is compared in visual learning understanding applications. Three image tasks and two video tasks of computer vision are investigated. The former mainly includes image classification, object detection, and image segmentation. The latter contains object tracking and video classification. It is significant for comparing different models' performance in various tasks on several public benchmark data sets. Finally, ten general problems are summarized, and the developing prospects of the visual Transformer are given in this review.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 109 of its 136 references that are in the map. First posted on arXiv 24 Mar 2022.

Builds on

109 of 136 references.

References · 109

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2017Squeeze-and-Excitation Networkscited by 4,763
  8. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  9. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  10. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  11. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  12. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
38 more
  1. 2017The Kinetics Human Action Video Datasetcited by 1,894
  2. 2021Vision Transformers for Dense Predictioncited by 1,789
  3. 2021ViViT: A Video Vision Transformercited by 1,610
  4. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,609
  5. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,552
  6. 2017Deformable Convolutional Networkscited by 1,481
  7. 2015Spatial Transformer Networkscited by 1,423
  8. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
  9. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  10. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  11. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,265
  12. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,218
  13. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  14. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  15. 2021Video Swin Transformercited by 1,090
  16. 2021Transformers in Vision: A Surveycited by 1,009
  17. 2021UNETR: Transformers for 3D Medical Image Segmentationcited by 954
  18. 2021CvT: Introducing Convolutions to Vision Transformerscited by 946
  19. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
  20. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  21. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  22. 2020Efficient Transformers: A Surveycited by 784
  23. 2021Transformer in Transformercited by 632
  24. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  25. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  26. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 526
  27. 2018Object Detection with Deep Learning: A Reviewcited by 524
  28. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 516
  29. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 515
  30. 2021Conditional DETR for Fast Training Convergencecited by 422
  31. 2021Transformer Trackingcited by 412
  32. 2019GhostNet: More Features from Cheap Operationscited by 410
  33. 2021Conditional Positional Encodings for Vision Transformerscited by 402
  34. 2019Selective Kernel Networkscited by 401
  35. 2021A Survey of Transformerscited by 399
  36. 2020TransTrack: Multiple Object Tracking with Transformercited by 370
  37. 2021Bottleneck Transformers for Visual Recognitioncited by 364
  38. 2020MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformerscited by 355

50 most cited of 109 All 109 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 1; 2025: 0; 2026: 1.

5 papers.

  1. 2023When Geoscience Meets Foundation Models: Towards General Geoscience Artificial Intelligence Systemcited by 13
  2. 2023Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformerscited by 9
  3. 2024PointMT: Efficient Point Cloud Analysis with Hybrid MLP-Transformer Architecturecited by 3
  4. 2023A Comprehensive Study of Vision Transformers in Image Classification Taskscited by 2
  5. 2026Attention-based graph neural networks: a surveycited by 1