A Theoretical Analysis of Feature Pooling in Visual Recognition on ShortScience.org

www.icml2010.org
sci-hub
scholar.google.com

A Theoretical Analysis of Feature Pooling in Visual Recognition
Boureau, Y-Lan and Ponce, Jean and LeCun, Yann
International Conference on Machine Learning - 2010 via Local Bibsonomy
Keywords: dblp

Summaries/Notes 1

[link] Summary by Martin Thoma 8 years ago

This paper analyzes max pooling and average pooling, as it is used in many convolutional neural networks (CNNs).

## Why pooling is used

* invariance to image transformations
* more compact representations (- remove irrelevant information)
* better robustness to noise and clutter


## Max pooling or average pooling?

No clear answer to that. Sometimes one seems to be better, sometimes the other, sometimes something in between.

This paper analyzes max pooling and average pooling, as it is used in many convolutional neural networks (CNNs).

Why pooling is used

invariance to image transformations
more compact representations (- remove irrelevant information)
better robustness to noise and clutter

Max pooling or average pooling?

No clear answer to that. Sometimes one seems to be better, sometimes the other, sometimes something in between.

Your comment:

Write your summary here (You can use $\LaTeX$ and markdown syntax):

Anon Private