Super-vector coding

Closed weights University of Illinois Urbana-Champaign (UIUC),NEC Laboratories,Rutgers University 1K parameters January 2010

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 Illinois Urbana-Champaign (UIUC),NEC Laboratories,Rutgers University
Organisation type
Academia,Industry,Academia
Country
United States of America
Published
1 January 2010
Authors
Xi Zhou, Kai Yu, Tong Zhang, and Thomas S. Huang

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Vision
Task
Image classification, Object recognition

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
1K

Somewhat low confidence, but it seems like the number of learnable parameters is the size of the codebook, plus parameters in the SVM used for classification. Since it is a linear SVM, there will be one parameter per input feature, plus a single bias term. So in total, 512 learnable codebook values, plus 513 SVM parameters = 1025 parameters

Training data
tokens

"PASCAL VOC 2007 consists of 9,963 images which are divided intothree subsets: training data (2501 images), validation data (2510 images), and test data (4952 images). PASCAL VOC 2009 consists of 14,743 images and correspondingly are divided into three subsets: training data(3473 images), validation data(3581 images), and testing data (7689 images)." PASCAL VOC 2009 is the larger experiment; images used in training is 3473 + 3581 = 7,054 For each image, the inputs for the codebook training are…

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

"Our experiments demonstrate that the proposed classification method achieves state-of-the-art accuracy on the well-known PASCAL benchmarks."

Record confidence
Speculative
Citations
696

Sources

Where this record came from and when it was last checked.

Reference
Image Classification using Super-Vector Coding of Local Image Descriptors
Last updated
28 November 2025

What the numbers mean

Where it came from

Super-vector coding was published by University of Illinois Urbana-Champaign (UIUC),NEC Laboratories,Rutgers University, in United States of America, in January 2010. It comes out of academia,Industry,Academia.

It works in Vision, and is recorded as doing image classification, Object recognition.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

How it was trained

Its inclusion criterion is sOTA improvement.

Answers

Super-vector coding — common questions

01

Who created Super-vector coding?

Super-vector coding was published by University of Illinois Urbana-Champaign (UIUC),NEC Laboratories,Rutgers University, based in United States of America, categorised as academia,Industry,Academia.

02

When was Super-vector coding released?

Super-vector coding was published in January 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.

03

What is Super-vector coding used for?

Super-vector coding works in Vision, and is recorded as handling image classification, Object recognition. These are the areas it was designed around; they describe intent rather than a hard boundary.

04

What GPU do I need to run Super-vector coding?

None. Super-vector coding 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.

05

Is Super-vector coding open source?

The licensing for Super-vector coding was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

06

How many parameters does Super-vector coding have?

Super-vector coding has 1K parameters. Somewhat low confidence, but it seems like the number of learnable parameters is the size of the codebook, plus parameters in the SVM used for classification. Since it is a linear SVM, there will be one parameter per input feature, plus a single bias term. So in total, 512 learnable codebook values, plus 513 SVM parameters = 1025 parameters. 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.

Source

Original publication

Record last updated 28 November 2025

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.