Template Adaptation
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
- University of Oxford
- Organisation type
- Academia
- Country
- United Kingdom of Great Britain and Northern Ireland
- Published
- 12 March 2016
- Authors
- Nate Crosswhite, J. Byrne, C. Stauffer, Omkar M. Parkhi, Qiong Cao, Andrew Zisserman
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Face recognition
- Approach
- Supervised
- Base model
- VGG-Face
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
- 138M
- Training data
- 7,797 tokens
Trains SVM on top of VGG-Face (VGG16 architecture). SVM parameters are not included in the estimate.
"IJB-A contains 5712 images and 2085 videos of 500 subjects, for an average of 11.4 images and 4.2 videos per subject." Unclear how the videos were converted to training images.
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Closed — provider access only
- Model access
- Unreleased
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Why it is tracked
- SOTA improvement
- Record confidence
- Likely
https://paperswithcode.com/sota/face-verification-on-ijb-a " Extensive performance evaluations on IJB-A show a surprising result, that perhaps the simplest method of template adaptation, combining deep convolutional network features with template specific linear SVMs, outperforms the state-of-the-art by a wide margin."
Sources
Where this record came from and when it was last checked.
- Reference
- Template Adaptation for Face Verification and Identification
- Last updated
- 28 November 2025
What the numbers mean
What this model is
Template Adaptation was published by University of Oxford, in the country recorded as United Kingdom of Great Britain and Northern Ireland, during March 2016. The publishing organisation is categorised as academia.
It works in the domain of Vision, and is recorded as performing the task of face recognition.
Its starting point was an existing base model, VGG-Face. That is the usual way a specialised model is produced.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
What went into building it
The training set ran to roughly 7,797 tokens of text.
The reason it appears in this catalogue at all: sOTA improvement.
Answers
Template Adaptation — common questions
Template Adaptation— how many parameters does it have?
It has a parameter count of 138M. Trains SVM on top of VGG-Face (VGG16 architecture). SVM parameters are not included in the estimate. 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.
Template Adaptation— who created it?
It was published by University of Oxford, based in United Kingdom of Great Britain and Northern Ireland, an organisation categorised as academia.
Template Adaptation— when was it released?
It was published in March 2016. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
Template Adaptation— what is it used for?
It works in the domain of Vision, and is recorded as handling the task of face recognition. These are the areas it was designed around; they describe intent rather than a hard boundary.
Template Adaptation— 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.
Template Adaptation— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
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.