ConvNet similarity metric
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
- New York University (NYU)
- Organisation type
- Academia
- Country
- United States of America
- Published
- 20 June 2005
- Authors
- S Chopra, R Hadsell, Y LeCun
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Face verification
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
- 140,000 tokens
The actual training set that was used contained 140,000 image pairs that were evenly split between genuine and impostor.
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Citations
- 4,059
Sources
Where this record came from and when it was last checked.
- Reference
- Learning a similarity metric discriminatively, with application to face verification
- Last updated
- 28 November 2025
What the numbers mean
What this model is
ConvNet similarity metric was published by New York University (NYU), in United States of America, in June 2005. The organisation is categorised as academia.
It works in Vision, and is recorded as doing face verification.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
What went into building it
Around 140,000 tokens went into training it.
Answers
ConvNet similarity metric — common questions
Who created ConvNet similarity metric?
ConvNet similarity metric was published by New York University (NYU), based in United States of America, categorised as academia.
When was ConvNet similarity metric released?
ConvNet similarity metric was published in June 2005. 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 ConvNet similarity metric used for?
ConvNet similarity metric works in Vision, and is recorded as handling face verification. These are the areas it was designed around; they describe intent rather than a hard boundary.
What GPU do I need to run ConvNet similarity metric?
None. ConvNet similarity metric 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 ConvNet similarity metric open source?
The licensing for ConvNet similarity metric 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 ConvNet similarity metric have?
No parameter count has been published for ConvNet similarity metric, 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.