Refined Max-Pooling and Unpooling Layers for Deep Convolutional Neural Networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216275%3A25530%2F16%3A39902263" target="_blank" >RIV/00216275:25530/16:39902263 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Refined Max-Pooling and Unpooling Layers for Deep Convolutional Neural Networks

Popis výsledku v původním jazyce

The main goal of this paper is the introduction of new pooling and unpooling layers suited for deep convolutional neural networks. To this end, a new approximation of max-pooling inversion has been designed. The idea behind this approximation is also introduced in this paper. It is demonstrated on pools of size 2 x 2, with a stride of 2. The widely used technique of switches is combined with interpolation to form the new approximation. For that purpose, an unconventional expression of the switches has been used. Such an expression, allows the right placement of maxima in a reconstruction of original data, as well as interpolation of all unknown values in the reconstruction using the known maxima. The introduced inversion has been implemented into the aforementioned refined pooling and unpooling layers. Since they are suited for deep convolutional networks, behavior of the layers in the feed-forward and backpropagation passes had to be solved. In this context, the introduced conception of the switches has been further developed. Specifically, feed-forward and backpropagation switches are considered in the refined layers. One version of feed-forward and three versions of backpropagation switches have been introduced within this paper. The refined pooling and unpooling layers have been tested on a simple convolutional auto-encoder in order to verify functionality of the conception.

Název v anglickém jazyce

Refined Max-Pooling and Unpooling Layers for Deep Convolutional Neural Networks

Popis výsledku anglicky

The main goal of this paper is the introduction of new pooling and unpooling layers suited for deep convolutional neural networks. To this end, a new approximation of max-pooling inversion has been designed. The idea behind this approximation is also introduced in this paper. It is demonstrated on pools of size 2 x 2, with a stride of 2. The widely used technique of switches is combined with interpolation to form the new approximation. For that purpose, an unconventional expression of the switches has been used. Such an expression, allows the right placement of maxima in a reconstruction of original data, as well as interpolation of all unknown values in the reconstruction using the known maxima. The introduced inversion has been implemented into the aforementioned refined pooling and unpooling layers. Since they are suited for deep convolutional networks, behavior of the layers in the feed-forward and backpropagation passes had to be solved. In this context, the introduced conception of the switches has been further developed. Specifically, feed-forward and backpropagation switches are considered in the refined layers. One version of feed-forward and three versions of backpropagation switches have been introduced within this paper. The refined pooling and unpooling layers have been tested on a simple convolutional auto-encoder in order to verify functionality of the conception.

Druh

D - Stať ve sborníku

CEP obor

BD - Teorie informace

OECD FORD obor

—

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2016

Kód důvěrnosti údajů

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

Název statě ve sborníku

Mendel 2016 : 22nd International Conference on Soft Computing

ISBN

978-80-214-5365-4

ISSN

1803-3814

e-ISSN

—

Počet stran výsledku

12

Strana od-do

131-142

Název nakladatele

Vysoké učení technické v Brně

Místo vydání

Brno

Místo konání akce

Brno

Datum konání akce

8. 6. 2016

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—