Discovering basic kernels in the first layer of a CNN

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17610%2F18%3AA1901U95" target="_blank" >RIV/61988987:17610/18:A1901U95 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Discovering basic kernels in the first layer of a CNN

Original language description

In our research, we are focused on a semantic description of feature maps and corresponding to them kernels that are used in Convolutional neural networks (CNN). A CNN is a hierarchically ordered computational tool that uses a training process to learn and extract abstract characteristics (features) of input objects. The extracted features have to approximate the original object sufficiently for a next stage (classification, regression, etc.). The first layer of a CNN extracts features by performing convolution operations with a number of kernels. Therefore, to study the semantic description of feature maps in the first layer, we should be focused on convolutional kernels (otherwise, weight vectors). We make a conjecture that in the first layer, a CNN learns the most typical image processing convolutional kernels, and they appear in subsequent layers as well. To confirm our claim, we have used 5 CNNs~cite{vgg,inception,resnet,mobilenet,alexnet} trained on the textit{ImageNet} dataset. In the first layer of selected CNNs, we have identified (after performing clustering) the following kernels: gradient kernels with various rotations, Gaussian kernels and texture extracting kernels (e.g., Gabor filters). Further, we have found kernels sensitive to certain color(s) (combinations) that might be dominant in the ImageNet.To conclude, our hypothesis seems to be correct, and a CNN indeed learns standard image processing convolution kernels. A relationship between kernels in further layers is a subject of the future research.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10102 - Applied mathematics

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2018

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the 19th International Student Conference on Applied Mathematics and Informatics

ISBN

9788074641121

ISSN

—

e-ISSN

—

Number of pages

1

Pages from-to

51-51

Publisher name

University of Ostrava

Place of publication

Ostrava

Event location

Malenovice

Event date

May 10, 2018

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—