Comparing Normalization Methods for Limited Batch Size Segmentation Neural Networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F20%3APU137022" target="_blank" >RIV/00216305:26220/20:PU137022 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/9163397" target="_blank" >https://ieeexplore.ieee.org/document/9163397</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TSP49548.2020.9163397" target="_blank" >10.1109/TSP49548.2020.9163397</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Comparing Normalization Methods for Limited Batch Size Segmentation Neural Networks

Popis výsledku v původním jazyce

The widespread use of Batch Normalization has enabled training deeper neural networks with more stable and faster results. However, the Batch Normalization works best using large batch size during training and as the state-of-theart segmentation convolutional neural network architectures are very memory demanding, large batch size is often impossible to achieve on current hardware. We evaluate the alternative normalization methods proposed to solve this issue on a problem of binary spine segmentation from 3D CT scan. Our results show the effectiveness of Instance Normalization in the limited batch size neural network training environment. Out of all the compared methods the Instance Normalization achieved the highest result with Dice coefficient = 0.96 which is comparable to our previous results achieved by deeper network with longer training time. We also show that the Instance Normalization implementation used in this experiment is computational timeefficient when compared to the network without any normalization method.

Název v anglickém jazyce

Comparing Normalization Methods for Limited Batch Size Segmentation Neural Networks

Popis výsledku anglicky

The widespread use of Batch Normalization has enabled training deeper neural networks with more stable and faster results. However, the Batch Normalization works best using large batch size during training and as the state-of-theart segmentation convolutional neural network architectures are very memory demanding, large batch size is often impossible to achieve on current hardware. We evaluate the alternative normalization methods proposed to solve this issue on a problem of binary spine segmentation from 3D CT scan. Our results show the effectiveness of Instance Normalization in the limited batch size neural network training environment. Out of all the compared methods the Instance Normalization achieved the highest result with Dice coefficient = 0.96 which is comparable to our previous results achieved by deeper network with longer training time. We also show that the Instance Normalization implementation used in this experiment is computational timeefficient when compared to the network without any normalization method.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2020

Kód důvěrnosti údajů

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

Název statě ve sborníku

2020 43rd International Conference on Telecommunications and Signal Processing (TSP)

ISBN

978-1-7281-6376-5

ISSN

—

e-ISSN

—

Počet stran výsledku

4

Strana od-do

677-680

Název nakladatele

Neuveden

Místo vydání

Neuveden

Místo konání akce

Milan, Italy

Datum konání akce

7. 7. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—