Fisher Vector image classifier
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
- Universidad Nacional de Cordoba,Inteligent Systems Lab Amsterdam,University of Amsterdam,LEAR Team,INRIA,Xerox Research Centre Europe (XRCE)
- Organisation type
- Academia,Academia,Academia,Academia,Industry
- Country
- Argentina, Netherlands, France
- Published
- 12 June 2013
- Authors
- orge Sanchez, Florent Perronnin, Thomas Mensink, Jakob Verbeek
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Image classification
- Numerical format
- FP32
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
- 4,500,000 tokens
Training compute
The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.
- Training compute
- 9.1 × 10¹³ FLOP
- How it was established
- Hardware
They use a Intel Xeon E5-2470 Processor for 2 hours. This can do 12,617 MOps/Sec (average test results, assuming they achieved a similar utilization) https://www.cpubenchmark.net/cpu.php?cpu=Intel+Xeon+E5-2470+%40+2.30GHz&id=2003 12617000000*2*60*60=90842400000000
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
- 2 hours
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Confident
- Citations
- 1,707
Sources
Where this record came from and when it was last checked.
- Reference
- Image Classification with the Fisher Vector: Theory and Practice
- Last updated
- 28 November 2025
What the numbers mean
What this model is
Fisher Vector image classifier was published by Universidad Nacional de Cordoba,Inteligent Systems Lab Amsterdam,University of Amsterdam,LEAR Team,INRIA,Xerox Research Centre Europe (XRCE), in the country recorded as Argentina, during June 2013. It comes out of an organisation categorised as academia,Academia,Academia,Academia,Industry.
It works in the domain of Vision, and is recorded as performing the task of image classification.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
Training and provenance
Training it took a computation budget of roughly 9.1 × 10¹³ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
Training consumed a corpus of around 4,500,000 tokens of text.
Answers
Fisher Vector image classifier — common questions
Fisher Vector image classifier— when was it released?
It was published in June 2013. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
Fisher Vector image classifier— what is it used for?
It works in the domain of Vision, and is recorded as handling the task of image classification. These are the areas it was designed around; they describe intent rather than a hard boundary.
Fisher Vector image classifier— how much compute was used to train it?
Training consumed around 9.1 × 10¹³ FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.
Fisher Vector image classifier— what GPU do I need to run it?
None. This 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.
Fisher Vector image classifier— is it open source?
The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
Fisher Vector image classifier— how many parameters does it have?
No parameter count has been published for it, which is why no memory or speed figure appears on this page.
Fisher Vector image classifier— who created it?
It was published by Universidad Nacional de Cordoba,Inteligent Systems Lab Amsterdam,University of Amsterdam,LEAR Team,INRIA,Xerox Research Centre Europe (XRCE), based in Argentina, an organisation categorised as academia,Academia,Academia,Academia,Industry.
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.