# Shared Embedding Spaces — Multimodal AI

Source: https://www.skillbyai.com/en/multimodal-ai/mm-shared-space

> Explain what a joint image-text embedding space is and measure alignment with cosine similarity.

## One space for pictures and words

If an image encoder and a text encoder both output vectors of the same length, we can train them so that an image and a caption describing it land **close together**, while unrelated pairs land far apart. The result is a **shared (joint) embedding space**. Closeness is usually measured with **cosine similarity**: the dot product of two vectors after each is scaled to length 1, giving a value between -1 and 1. Once such a space exists, many tasks become nearest-neighbour search: find images for a text query, find captions for an image, cluster a photo collection, or detect near-duplicates. The two encoders never generate anything; they only produce vectors. This is why joint-embedding models such as CLIP are cheap to use at scale: you embed your image collection once, store the vectors in a vector index, and every query costs one text encoding plus a fast similarity search.

## Two towers, one space

A dual-encoder model runs an image tower and a text tower separately, then compares their normalised outputs in a shared space.

![Three connected stages: image and text encoders, normalised embeddings, similarity matrix.](assets/figures/multimodal-ai/section-4-map.svg) — Figure 4.1: image encoder + text encoder -> L2-normalised embeddings in a shared space -> cosine similarity matrix.

## A map of a city

Think of the shared space as a city map where every photo and every sentence gets a pin. "Chai stall at a railway station" and a photo of exactly that are pinned on the same street, while a photo of a cricket match sits across town.

**Quiz:** Two unit-length vectors have a cosine similarity of 1.0. What does that mean?

- [ ] They are unrelated
- [ ] They point in opposite directions
- [ ] One of them is a zero vector
- [x] They point in exactly the same direction

*Answer:* They point in exactly the same direction. Cosine similarity is 1 when the angle between the vectors is zero, i.e. they point the same way.