Invariant Convolutional Networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F23%3A00576905" target="_blank" >RIV/67985556:_____/23:00576905 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/IPTA59101.2023.10319998" target="_blank" >http://dx.doi.org/10.1109/IPTA59101.2023.10319998</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/IPTA59101.2023.10319998" target="_blank" >10.1109/IPTA59101.2023.10319998</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Invariant Convolutional Networks

Popis výsledku v původním jazyce

Neural networks are often trained on datasets, that are not fully representative of the expected query images. Many times, the difference stem from the query images being taken in sub-optimal conditions. The most common defects are rotation, scale, blur, noise and intensity & contrast change which were all thoroughly studied and described. In this paper we propose a novel neural network architecture which is invariant to such degradations by design. We incorporate the knowledge build for classical methods directly into the network architecture providing an alternative to the augmentation of the training dataset. In the experiments, the proposed solution outperforms the classical augmentation technique in both accuracy and computational resources needed.n

Název v anglickém jazyce

Invariant Convolutional Networks

Popis výsledku anglicky

Neural networks are often trained on datasets, that are not fully representative of the expected query images. Many times, the difference stem from the query images being taken in sub-optimal conditions. The most common defects are rotation, scale, blur, noise and intensity & contrast change which were all thoroughly studied and described. In this paper we propose a novel neural network architecture which is invariant to such degradations by design. We incorporate the knowledge build for classical methods directly into the network architecture providing an alternative to the augmentation of the training dataset. In the experiments, the proposed solution outperforms the classical augmentation technique in both accuracy and computational resources needed.n

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20204 - Robotics and automatic control

Projekt

<a href="/cs/project/GA21-03921S" target="_blank" >GA21-03921S: Inverzní problémy ve zpracování obrazu</a><br>

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2023

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of The 12th International Conference on Image Processing Theory, Tools and Applications (IPTA 2023)

ISBN

979-8-3503-2541-6

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

10319998

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Paris

Datum konání akce

16. 10. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—