Invariant Convolutional Networks
The result's identifiers
Result code in 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>
Result on the web
<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>
Alternative languages
Result language
angličtina
Original language name
Invariant Convolutional Networks
Original language description
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
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
20204 - Robotics and automatic control
Result continuities
Project
<a href="/en/project/GA21-03921S" target="_blank" >GA21-03921S: Inverse problems in image processing</a><br>
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of The 12th International Conference on Image Processing Theory, Tools and Applications (IPTA 2023)
ISBN
979-8-3503-2541-6
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
10319998
Publisher name
IEEE
Place of publication
Piscataway
Event location
Paris
Event date
Oct 16, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—