ACF-WIDER
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
- Chinese Academy of Sciences
- Organisation type
- Academia
- Country
- China
- Published
- 15 July 2014
- Authors
- Binh Yang, Junjie Yan, Zhen Lei, S. Li
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Face detection
- 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
- 6.1K
- Training data
- 144,448 tokens
The paper trains a decision tree ensemble. “we choose 2048 as the number of weak classifiers contained in the soft cascade. As each weak classifier is a depth-2 decision tree, it takes only two comparing operations to apply a weak classifier, which is quite fast.” Parameters: 2048*(2^2-1)=6144
“there are in total 36, 112 positive samples and 108, 336 negative samples selected from AFLW”
Training compute
The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.
- Training compute
- 7.6 × 10¹³ FLOP
- How it was established
- Hardware
Training compute: 10.2 minutes * 4 * 3.9* 10^9 cycles per second * 16 FLOP per cycle * 0.5 = 7.638*10^13 FLOPs “on a PC with Intel Core i7-3770 CPU and 16GB RAM” Ivy Bridge, 4 cores, 3.9GHz, 16 FP32 FLOP/cycle (https://en.wikipedia.org/wiki/Floating_point_operations_per_second ) “and 10.2 mins for multi-scale version.”
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Chips used
- 1
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
- Training code
- 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
- Confident
https://paperswithcode.com/sota/face-detection-on-wider-face-medium "the multi-view face detector using aggregate channel features shows competitive performance against state-of-the-art algorithms on AFW and FDDB test-sets, while runs at 42 FPS on VGA images."
Sources
Where this record came from and when it was last checked.
- Reference
- Aggregate channel features for multi-view face detection
- Last updated
- 28 November 2025
What the numbers mean
About this model
ACF-WIDER was published by Chinese Academy of Sciences, in China, in July 2014. academia is the category the publisher falls under.
It works in Vision, and is recorded as doing face detection.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
What went into building it
Producing it required around 7.6 × 10¹³ FLOP of arithmetic, which is a statement about the training budget rather than about inference.
The training set ran to roughly 144,448 tokens.
The reason it appears in this catalogue at all is sOTA improvement.
Answers
ACF-WIDER — common questions
Who created ACF-WIDER?
ACF-WIDER was published by Chinese Academy of Sciences, based in China, categorised as academia.
When was ACF-WIDER released?
ACF-WIDER was published in July 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.
What is ACF-WIDER used for?
ACF-WIDER works in Vision, and is recorded as handling face detection. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
How much compute was used to train ACF-WIDER?
Around 7.6 × 10¹³ FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.
What GPU do I need to run ACF-WIDER?
None. ACF-WIDER 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 ACF-WIDER open source?
No. ACF-WIDER has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does ACF-WIDER have?
ACF-WIDER has 6.1K parameters. The paper trains a decision tree ensemble. “we choose 2048 as the number of weak classifiers contained in the soft cascade. As each weak classifier is a depth-2 decision tree, it takes only two comparing operations to apply a weak classifier, which is quite fast.” Parameters: 2048*(2^2-1)=6144. 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.
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.