# Image embeddings Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/image-embeddings
> Markdown URL: https://aitinkerers.org/technologies/image-embeddings.md
> Technology record last updated: 2026-03-12T23:10:07Z
> Generated: 2026-09-22T09:47:29Z

Image embeddings are compact, fixed-length numerical vectors (e.g., 512-dimensional) that encode an image's high-level semantic content, enabling efficient comparison and machine understanding.

This is the core technology: translating high-dimensional image data into a compact, fixed-length vector—a numeric 'fingerprint' that captures the image's semantic meaning, not just raw pixels. Deep learning models (like CNNs, Vision Transformers, or multimodal systems like OpenAI's CLIP) generate these vectors. Crucially, visual similarity translates directly to vector proximity in the embedding space: close vectors mean similar images. This vector representation is the backbone for high-performance computer vision tasks: powering rapid nearest-neighbor search, clustering, e-commerce visual search, and zero-shot classification on multi-million-image datasets.

- Official technology site: https://voxel51.com/docs/fiftyone/glossary/image_embeddings.html
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Hotdogs: a game about drawing weird dogs](https://zurich.aitinkerers.org/talks/rsvp_dwqsVmNMYUw)

After the Gandalf prompt injection game (https://gandalf.lakera.ai/) that I designed took off, we wanted to make a similar kind of game but with images instead of text. What we came up with was Hotdogs: your goal is to sketch an image such that it's recognized as a dog according to an image classifier, but also make it as different as possible from the other dogs people have submitted (measured using image embeddings). In the end, we deemed it too silly to be associated with the company, but it's the right amount of silly for me! Joint work with Aashna Majmudar, Pep Borrell, and Lena Shturba.

- Event context: AI Tinkerers Zurich - May 8 — 2024-05-08 — Zürich
- Public talk page: https://zurich.aitinkerers.org/talks/rsvp_dwqsVmNMYUw

## Related Technologies

- [AI](https://aitinkerers.org/technologies/ai) ([Markdown](https://aitinkerers.org/technologies/ai.md)) — 55 public demos
- [Image Classifier](https://aitinkerers.org/technologies/image-classifier) ([Markdown](https://aitinkerers.org/technologies/image-classifier.md)) — 2 public demos