Skip to contentScholarGate
LibraryBookshelfDeskReview StudioAssistant
Sign in
On this page
IntuitionHow it worksWhen to use itStrengths & limitationsCommon pitfallsApplicationsFrequently asked🔒 Read the full methodSourcesRelated methods
Cite this pageSpotted an issue on this page? Report or suggest a fix →
Home›Deep learning›Vision Transformer
Machine learning

Vision Transformer

Vision Transformer (ViT) · Also known as: Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images

The Vision Transformer (ViT), introduced by Dosovitskiy and colleagues in 2021, splits an image into fixed-size patches, treats those patches as a sequence, and applies the Transformer self-attention mechanism to image classification. Given enough training data, it surpasses convolutional neural networks (CNNs).

ScholarGate
  1. Machine learning
  2. v1
  3. 2 Sources
  4. PUBLISHED
Cite this page →
Tools & resources
Download slides
Learn & explore

Read the full method

Members only

Sign in with a free account to read this section.

Sign in

Method map

The neighbourhood of related methods — select a node to explore.

Vision Transformer
Diffusion ModelGenerative Adversarial N…Random ForestSupport Vector MachineVariational AutoencoderBERT Fine-TuningCLIPDomain-adaptive transfor…Domain-adaptive vision t…Explainable Vision Trans…

+27 more

When to use it

Use ViT for image classification or prediction on continuous (pixel) image data when you have a large dataset — on the order of 1000 or more images, and ideally far more — and access to a GPU. It works best with a large pre-training corpus or transfer learning from a pre-trained model. On small image datasets (below a few hundred images) ViT cannot learn its patch-based attention reliably, and a CNN or classical machine-learning method such as Random Forest or SVM is the safer choice.

Strengths & limitations

Strengths
  • Surpasses CNNs on large image datasets by modelling global relationships through self-attention.
  • Treats an image as a sequence of patches, applying the proven Transformer architecture to vision.
  • Captures long-range dependencies across the whole image, not just local neighbourhoods.
  • Benefits strongly from large-scale pre-training and transfer learning to pre-trained checkpoints.
  • Does not assume normally distributed data.
Limitations
  • Requires a large training set (about 1000 images or more); on small data it underperforms CNNs.
  • A GPU is required, and training from scratch is data- and compute-hungry.
  • On very small datasets (below a few hundred images) patch-based attention fails to learn reliably.
  • Strong results typically depend on a large pre-training corpus or transfer learning rather than training from scratch.

Frequently asked

How is ViT different from a CNN?

A CNN processes an image through local convolutional filters, while ViT splits the image into fixed-size patches, treats them as a sequence, and uses self-attention so any patch can relate to any other. This lets ViT model global relationships and, on large datasets, surpass CNNs.

How much data does ViT need?

ViT is data-hungry: it works best with around 1000 or more images and a large pre-training corpus. Below a few hundred images its patch-based attention cannot learn reliably, and a CNN or classical method is preferable.

Do I need a GPU?

Yes. ViT requires a GPU, and training it is data- and compute-intensive. Using a pre-trained checkpoint with transfer learning reduces the burden considerably.

What if my image dataset is small?

On small datasets ViT underperforms. Below roughly 500 images consider a method like Random Forest, and below a few hundred a CNN or SVM is the safer choice, or rely on transfer learning from a pre-trained model.

Sources

  1. Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR. link ↗
  2. Touvron, H. et al. (2021). Training Data-Efficient Image Transformers. ICML. link ↗

How to cite this page

ScholarGate. (2026, June 1). Vision Transformer (ViT). ScholarGate. https://scholargate.app/en/deep-learning/vision-transformer

Related methods

Diffusion ModelGenerative Adversarial NetworkRandom ForestSupport Vector MachineVariational Autoencoder

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

  • Diffusion ModelDeep learning↔ compare
  • Generative Adversarial NetworkDeep learning↔ compare
  • Random ForestMachine learning↔ compare
  • Support Vector MachineMachine learning↔ compare
  • Variational AutoencoderDeep learning↔ compare
Compare side by side →

Referenced by

BERT Fine-TuningCLIPDomain-adaptive transformerDomain-adaptive vision transformerExplainable Vision TransformerFine-Tuned Vision TransformerGPT Fine-TuningImage ClassificationKolmogorov-Arnold NetworksLoRA and PEFTMamba (State Space Model)Masked AutoencodersMultilingual vision transformerMultimodal BERT-based ClassificationMultimodal NLPMultimodal Semantic SegmentationMultimodal TransformerMultimodal Vision TransformerSegment Anything ModelSelf-supervised GANSelf-supervised Image ClassificationSelf-supervised Instance SegmentationSelf-supervised Semantic SegmentationSelf-supervised Vision TransformerSemi-supervised Vision TransformerSimCLRSpatial-Temporal GCNSwin TransformerTimeGPTVision MambaWeakly Supervised Object DetectionWeakly supervised vision transformer

Similar methods

Fine-Tuned Vision TransformerMultimodal Vision TransformerSemi-supervised Vision TransformerMultilingual vision transformerCNN Image ClassificationWeakly supervised vision transformerSelf-supervised Vision TransformerExplainable Vision Transformer

Related reference concepts

Object Recognition and DetectionConvolutional and Sequence ModelsSelf-Supervised and Representation LearningComputer VisionDeep LearningImage Segmentation

Spotted an issue on this page? Report or suggest a fix →

ScholarGate — Vision Transformer (Vision Transformer (ViT)). Retrieved 2026-07-21 from https://scholargate.app/en/deep-learning/vision-transformer · Dataset: https://doi.org/10.5281/zenodo.20539026
Quick facts
Originator
Dosovitskiy, A. et al.
Year
2021
Type
Transformer architecture for images (self-attention over patches)
Task
Image classification & prediction
MinSample
1000
RequiresGpu
Yes
Related methods
Diffusion ModelGenerative Adversarial NetworkRandom ForestSupport Vector MachineVariational Autoencoder
ScholarGate

A content-first reference library for research methods — what each one is, how it works, and where it comes from.

Open data (CC-BY)

Explore

  • Library
  • Search the library…
  • Browse by field
  • Fields
  • Journey
  • Compare
  • Which method?

Reference

  • Subjects
  • Atlas
  • Glossary
  • Methodology
  • Philosophy

Your tools

  • Bookshelf
  • Desk
  • Chat

Company

  • About
  • Pricing
  • Contact
  • Suggest a method

Entries are compiled from published sources for reference. Verifying the accuracy and suitability of any information for your own use remains your responsibility.

© 2026 ScholarGate · A research-method reference library
  • Privacy
  • Cookies
  • Terms
  • Delete account