Course contentsShow
← Machine Learning and Deep Learning
Lesson 1338 of 3,53830. Vision TransformersFree lesson

Image Patches as Tokens

How images are divided into fixed-size patches that serve as the basic input units.

Image Patches as Tokens

What you'll learn: How Vision Transformers treat image regions like words by splitting images into fixed-size patches.

The Core Idea

In natural language processing, Transformers process text as a sequence of tokens (words or subwords). Vision Transformers (ViTs) apply the same principle to images by dividing them into fixed-size patches that serve as the basic input units—essentially treating each patch as a "visual token."

Think of it like cutting a photograph into a grid of equally-sized squares, similar to a jigsaw puzzle. Each square becomes one token that the Transformer processes, just like it would process individual words in a sentence.

How It Works

Instead of processing pixels individually (which would be computationally prohibitive), an image is split into non-overlapping patches:

  1. Divide the image: A 224×224 pixel image might be split into 16×16 pixel patches
  2. Create a grid: This produces a 14×14 grid (196 total patches)
  3. Flatten each patch: Each patch is converted into a vector
  4. Sequence of tokens: These 196 patch vectors become the input sequence to the Transformer

For example, with patch size 16×16:

  • Each patch contains 16 × 16 × 3 = 768 values (for RGB images)
  • The entire image becomes a sequence of patches, just like a sentence is a sequence of words

Why Patches Matter

Patches balance computational efficiency with spatial information. Too small, and you have too many tokens; too large, and you lose fine-grained detail. The patch size becomes a hyperparameter that affects both model performance and computational cost.

Key Takeaway: Vision Transformers convert images into sequences by dividing them into fixed-size patches, treating each patch as a token analogous to words in NLP, enabling Transformer architectures to process visual data.