Unproportional mosaicing
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17610%2F22%3AA2302FC1" target="_blank" >RIV/61988987:17610/22:A2302FC1 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.34630/20734" target="_blank" >http://dx.doi.org/10.34630/20734</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.34630/20734" target="_blank" >10.34630/20734</a>
Alternative languages
Result language
angličtina
Original language name
Unproportional mosaicing
Original language description
Data shift is gap between data distribution used for training and data distribution encountered in real-world. Data augmentations help narrow the gap by generating new data samples, increasing data variability, and data space coverage. We present new data augmentation: Unproportinal mosaicing. Our augmentation randomly splits an image into various-sized blocks and swap their content (pixels) while maintaining block sizes. Our method achieves a lower error rate when combined with the other state-of-the-art augmentations.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10102 - Applied mathematics
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
International Conference on Mathematical Analysis and Applications in Science and Engineering ? Book of Extended Abstracts
ISBN
978-989-53496-3-0
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
357-360
Publisher name
Polytechnic of Porto. School of Engineering
Place of publication
Porto
Event location
Porto
Event date
Jun 27, 2022
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—