Fisher-Boost
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 Research Centre Europe (XRCE)
- Organisation type
- Industry
- Country
- France
- Published
- 5 September 2010
- Authors
- Florent Perronnin, Jorge Sánchez, Thomas Mensink
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.
- Training data
- 350,000 tokens
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
- 22 hours
"Extracting and projecting the SIFT features for the 350K training images takes approx. 15h (150ms / image), learning the GMM on a random subset of 1M descriptors approx. 30 min, computing the Fisher vectors. Improving the Fisher Kernel for Large-Scale Image Classification 155 approx. 4h (40ms / image) and learning the 18 classifiers approx. 2h (7 min / class). " 15 + 0.5 + 4 + 2 = 21.5 hours
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Unknown
- Citations
- 3,062
Sources
Where this record came from and when it was last checked.
- Reference
- Improving the Fisher Kernel for Large-Scale Image Classification
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
Fisher-Boost was published by Xerox Research Centre Europe (XRCE), in France, in September 2010. It comes out of industry.
It works in Vision, and is recorded as doing image classification.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
How it was trained
Around 350,000 tokens went into training it.
Answers
Fisher-Boost — common questions
How many parameters does Fisher-Boost have?
No parameter count has been published for Fisher-Boost, which is why no memory or speed figure appears on this page.
Who created Fisher-Boost?
Fisher-Boost was published by Xerox Research Centre Europe (XRCE), based in France, categorised as industry.
When was Fisher-Boost released?
Fisher-Boost was published in September 2010. 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-Boost used for?
Fisher-Boost 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 Fisher-Boost?
None. Fisher-Boost 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-Boost open source?
The licensing for Fisher-Boost was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
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.