Deeply-supervised nets

Closed weights Microsoft Research September 2014

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
Microsoft Research
Organisation type
Industry
Country
United States of America
Published
18 September 2014
Authors
Chen-Yu Lee, Saining Xie, Patrick Gallagher, Zhengyou Zhang, Zhuowen Tu

What it does

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

Domain
Vision
Task
Image classification, Digit 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.

Training data
598,388 tokens

60000+50000+60000+600000

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
Highly cited,SOTA improvement

our experimental result on benchmark datasets shows significant performance gain over existing methods (e.g. all state-of-the-art results on MNIST, CIFAR-10, CIFAR-100, and SVHN).

Citations
2,509

Sources

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

Reference
Deeply-Supervised Nets
Last updated
28 November 2025

What the numbers mean

About this model

Deeply-supervised nets was published by Microsoft Research, in United States of America, in September 2014. It comes out of industry.

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

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

What went into building it

The training set ran to roughly 598,388 tokens.

The reason it appears in this catalogue at all is highly cited,SOTA improvement.

Answers

Deeply-supervised nets — common questions

01

What GPU do I need to run Deeply-supervised nets?

None. Deeply-supervised nets 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.

02

Is Deeply-supervised nets open source?

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

03

How many parameters does Deeply-supervised nets have?

No parameter count has been published for Deeply-supervised nets, which is why no memory or speed figure appears on this page.

04

Who created Deeply-supervised nets?

Deeply-supervised nets was published by Microsoft Research, based in United States of America, categorised as industry.

05

When was Deeply-supervised nets released?

Deeply-supervised nets was published in September 2014. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

06

What is Deeply-supervised nets used for?

Deeply-supervised nets works in Vision, and is recorded as handling image classification, Digit recognition. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

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.