CNN Ensemble Robust to Rotation Using Radon Transform

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F23%3A00577116" target="_blank" >RIV/67985556:_____/23:00577116 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/IPTA59101.2023.10320086" target="_blank" >http://dx.doi.org/10.1109/IPTA59101.2023.10320086</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/IPTA59101.2023.10320086" target="_blank" >10.1109/IPTA59101.2023.10320086</a>

Jazyk výsledku

angličtina

Název v původním jazyce

CNN Ensemble Robust to Rotation Using Radon Transform

Popis výsledku v původním jazyce

A great deal of attention has been paid to alternative techniques to data augmentation in the literature. Their goal is to make convolutional neural networks (CNNs) invariant or at least robust to various transformations. In this paper, we present an ensemble model combining a classic CNN with an invariant CNNnwhere both were trained without any augmentation. The goal is to preserve the performance of the classic CNN on nondeformed images (where it is supposed to classify more accurately) and the performance of the invariant CNN on deformed images (where it is the other way around). The combination is controlled by another network which outputs a coefficient that determines the fusion rule of the two networks. The auxiliary network is trained to output the coefficient depending on the intensity of the image deformation. In the experiments, we focus on rotation as a simple and most frequently studied case of transformation. In addition, we present a network invariant to rotation that is fed with the Radon transform of the input images. The performance of this network is tested on rotated MNIST and is further used in the ensemble whose performance is demonstrated on the CIFAR10- dataset.

Název v anglickém jazyce

CNN Ensemble Robust to Rotation Using Radon Transform

Popis výsledku anglicky

A great deal of attention has been paid to alternative techniques to data augmentation in the literature. Their goal is to make convolutional neural networks (CNNs) invariant or at least robust to various transformations. In this paper, we present an ensemble model combining a classic CNN with an invariant CNNnwhere both were trained without any augmentation. The goal is to preserve the performance of the classic CNN on nondeformed images (where it is supposed to classify more accurately) and the performance of the invariant CNN on deformed images (where it is the other way around). The combination is controlled by another network which outputs a coefficient that determines the fusion rule of the two networks. The auxiliary network is trained to output the coefficient depending on the intensity of the image deformation. In the experiments, we focus on rotation as a simple and most frequently studied case of transformation. In addition, we present a network invariant to rotation that is fed with the Radon transform of the input images. The performance of this network is tested on rotated MNIST and is further used in the ensemble whose performance is demonstrated on the CIFAR10- dataset.

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

10320086

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

—