Fisher Kernel GMM
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
- Xerox
- Organisation type
- Industry
- Country
- United States of America
- Published
- 16 July 2007
- Authors
- Florent Perronnin, Christopher Dance
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Image classification
- Approach
- Supervised
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.
- Training data
- 570,000 tokens
"Approximately 30K images were available for training and 5K for testing. Both sets were manually multi-labeled"
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Wall-clock time
- 3 hours
"With Fisher kernels, the training cost is reduced down to approximately 2h30."
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Likely
- Citations
- 1,915
Sources
Where this record came from and when it was last checked.
- Reference
- Fisher kernels on visual vocabularies for image categorization
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
Fisher Kernel GMM was published by Xerox, in United States of America, in July 2007. The organisation is categorised as industry.
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.
What went into building it
The training set ran to roughly 570,000 tokens.
Answers
Fisher Kernel GMM — common questions
Who created Fisher Kernel GMM?
Fisher Kernel GMM was published by Xerox, based in United States of America, categorised as industry.
When was Fisher Kernel GMM released?
Fisher Kernel GMM was published in July 2007. 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 Fisher Kernel GMM used for?
Fisher Kernel GMM works in Vision, and is recorded as handling image classification. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
What GPU do I need to run Fisher Kernel GMM?
None. Fisher Kernel GMM 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 Fisher Kernel GMM open source?
The licensing for Fisher Kernel GMM 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 Fisher Kernel GMM have?
No parameter count has been published for Fisher Kernel GMM, which is why no memory or speed figure appears on this page.
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.