Domain 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 Maryland
- Organisation type
- Academia
- Country
- United States of America
- Published
- 6 November 2011
- Authors
- Raghuraman Gopalan, Ruonan Li, Rama Chellappa
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Object recognition
- 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.
- Parameters
- 15.3K
- Training data
- 2,790 tokens
Did not take into account initial image feature extraction, only novel stuff. 1. Perform PCA on the feature matrices from both domains. Learnable parameters are projection matrices. = 800 (# features) x 200 (reduced dimension) x 2 (once per subdomain) 2. Perform partial least squares regression. Learnable parameters are Matrix P with dimensions 200 (# features) x 30 (dimension of latent space) Matrix Q with dimensions 1 (# responses) x 30 (dimension of latent space) Projection matrix of X ont…
Dataset introduced in 'Adapting Visual Category Models to New Domains'
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Citations
- 1,071
Sources
Where this record came from and when it was last checked.
- Reference
- Domain Adaptation for Object Recognition: An Unsupervised Approach
- Last updated
- 28 November 2025
What the numbers mean
About this model
Domain Adaptation was published by University of Maryland, in the country recorded as United States of America, during November 2011. The category the publisher falls under is academia.
It works in the domain of Vision, and is recorded as performing the task of object recognition.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
Training and provenance
It was trained on a corpus of about 2,790 tokens of text.
Answers
Domain Adaptation — common questions
Domain Adaptation— when was it released?
It was published in November 2011. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
Domain Adaptation— what is it used for?
It works in the domain of Vision, and is recorded as handling the task of object recognition. 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.
Domain 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.
Domain Adaptation— 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.
Domain Adaptation— how many parameters does it have?
It has a parameter count of 15.3K. Did not take into account initial image feature extraction, only novel stuff. 1. Perform PCA on the feature matrices from both domains. Learnable parameters are projection matrices. = 800 (# features) x 200 (reduced dimension) x 2 (once per subdomain) 2. Perform partial least squares regression. Learnable parameters are Matrix P with dimensions 200 (# features) x 30 (dimension of latent space) Matrix Q with dimensions 1 (# responses) x 30 (dimension of latent space) Projection matrix of X onto latent space: 200 (# features) x 30 (dimension of latent space) Projection matrix of Y onto latent space: 1 (# responses) x 30 (dimension of latent space). 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.
Domain Adaptation— who created it?
It was published by University of Maryland, based in United States of America, an organisation categorised as academia.
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.