A Perspective of the Noise Removal for Faster Neural Network Training
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F19%3APU134020" target="_blank" >RIV/00216305:26220/19:PU134020 - isvavai.cz</a>
Výsledek na webu
<a href="https://ieeexplore.ieee.org/document/8970907" target="_blank" >https://ieeexplore.ieee.org/document/8970907</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ICUMT48472.2019.8970907" target="_blank" >10.1109/ICUMT48472.2019.8970907</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
A Perspective of the Noise Removal for Faster Neural Network Training
Popis výsledku v původním jazyce
Image classification is widely used within image processing area. It is known that insufficient amount of data has negative impact on the training of neural networks in terms of accuracy, convergence speed and in some cases even in the inability to converge. On the other hand, big amount of data significantly increases the training time and costs needed for model creation. Every training sample contains the part valuable for decision (face in case of this paper) and noise, i.e. background of the object. This paper introduces method of iterative noise removal during the training with combination with the transfer learning to optimize the speed of the training process. We show the combination of proposed noise removal and transfer learning leads to more effective training process and enables to learn also from limited data sets. The main contribution of this paper is a proposed method that reduces training time and it is able to accelerate the process in average by 69%. The method was tested on binary classification of two persons from LFW database.
Název v anglickém jazyce
A Perspective of the Noise Removal for Faster Neural Network Training
Popis výsledku anglicky
Image classification is widely used within image processing area. It is known that insufficient amount of data has negative impact on the training of neural networks in terms of accuracy, convergence speed and in some cases even in the inability to converge. On the other hand, big amount of data significantly increases the training time and costs needed for model creation. Every training sample contains the part valuable for decision (face in case of this paper) and noise, i.e. background of the object. This paper introduces method of iterative noise removal during the training with combination with the transfer learning to optimize the speed of the training process. We show the combination of proposed noise removal and transfer learning leads to more effective training process and enables to learn also from limited data sets. The main contribution of this paper is a proposed method that reduces training time and it is able to accelerate the process in average by 69%. The method was tested on binary classification of two persons from LFW database.
Klasifikace
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)
Návaznosti výsledku
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)<br>S - Specificky vyzkum na vysokych skolach
Ostatní
Rok uplatnění
2019
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název statě ve sborníku
2019 11th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT)
ISBN
978-1-7281-5763-4
ISSN
—
e-ISSN
—
Počet stran výsledku
4
Strana od-do
1-4
Název nakladatele
Neuveden
Místo vydání
Dublin
Místo konání akce
Dublin
Datum konání akce
28. 10. 2019
Typ akce podle státní příslušnosti
WRD - Celosvětová akce
Kód UT WoS článku
000540651700047