Bayesian object categorizer

Closed weights California Institute of Technology,University of Oxford 0.1K parameters October 2003

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
California Institute of Technology,University of Oxford
Organisation type
Academia,Academia
Country
United States of America, United Kingdom of Great Britain and Northern Ireland
Published
13 October 2003
Authors
Li Fei-Fei, Rob Fergus, Pietro Perona

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Vision
Task
Image classification

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters
0.1K

citation from section 2.1: In the constellation model, the dimensionality of \theta is large (~ 100)

Training data
20 tokens

description of Figure 1 "This dataset is obtained by collecting images through the Google image search engine (www.google.com). The keyword “things” is used to obtain hundreds of random images. "

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Speculative
Citations
806

Sources

Where this record came from and when it was last checked.

Reference
A Bayesian Approach to Unsupervised One-Shot Learning of Object Categories
Last updated
28 November 2025

What the numbers mean

Background

Bayesian object categorizer was published by California Institute of Technology,University of Oxford, in United States of America, in October 2003. It comes out of academia,Academia.

It works in Vision, and is recorded as doing image classification.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

Training and provenance

Around 20 tokens went into training it.

Answers

Bayesian object categorizer — common questions

01

When was Bayesian object categorizer released?

Bayesian object categorizer was published in October 2003. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

02

What is Bayesian object categorizer used for?

Bayesian object categorizer works in Vision, and is recorded as handling image classification. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

03

What GPU do I need to run Bayesian object categorizer?

None. Bayesian object categorizer is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

04

Is Bayesian object categorizer open source?

The licensing for Bayesian object categorizer was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

05

How many parameters does Bayesian object categorizer have?

Bayesian object categorizer has 0.1K parameters. citation from section 2.1: In the constellation model, the dimensionality of \theta is large (~ 100). That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

06

Who created Bayesian object categorizer?

Bayesian object categorizer was published by California Institute of Technology,University of Oxford, based in United States of America, categorised as academia,Academia.

Source

Original publication

Record last updated 28 November 2025

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.