What is Image Token?

Why does Image Token matter?

Turning visual input into a sequence lets transformer-style components process images together with text or other tokenized modalities.

Image Token in practice

Document whether tokens are continuous patches or discrete codes, preserve spatial position, test resolution and aspect-ratio changes, and count visual tokens in the model's input budget.

What is the common confusion about Image Token?

An image token is not necessarily one pixel, one object, or one fixed physical area. Its scope follows the visual encoder or tokenizer.

Learn Image Token in the course

Start with

• Vision-Language Models — The ViT-MLP-LLM Pattern

  A vision encoder converts an image into tokens. An MLP projector maps those tokens into the LLM's embedding space. A language model does the rest.

  Phase 04: Computer Vision

Taught in Phase 04: Computer Vision.

Related terms

• Patch EmbeddingA learned projection that converts an image patch into a fixed-width vector used as one element of a transformer input sequence.
• TokenAn integer identifier produced by a model-specific tokenizer from text, bytes, images, audio, or another input representation.
• VAE (Variational Autoencoder)A latent-variable model trained with a reconstruction objective and a regularization term that keeps an approximate posterior close to a…
• Vision Transformer (ViT)A vision architecture that represents an image as a sequence of patch embeddings with position information and processes that sequence…

Sources

• Vision Transformer
• VQ-VAE

More terms in Multimodal systems

• Audio Token
• Automatic Speech Recognition (ASR)
• Cross-Attention
• Early Fusion
• Late Fusion
• Modality
• Modality Alignment
• Multimodal Fusion
• Multimodal Model
• Patch Embedding
• Shared Embedding Space
• Vision-Language Model (VLM)
• Vision Transformer (ViT)
• Visual Grounding

Open the Multimodal systems list in the glossary