Bayesian object categorizer
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
- Training data
- 20 tokens
citation from section 2.1: In the constellation model, the dimensionality of \theta is large (~ 100)
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
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.
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.
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.
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.
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.
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.
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.