Synthetic dataset for compositional learning

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17610%2F18%3AA1901VAS" target="_blank" >RIV/61988987:17610/18:A1901VAS - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1142/11069" target="_blank" >http://dx.doi.org/10.1142/11069</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1142/11069" target="_blank" >10.1142/11069</a>

Result language
angličtina
Original language name
Synthetic dataset for compositional learning
Original language description
This contribution presents a framework for a generation of synthetic images. The framework is built on top of the Unreal Engine 4, a software kit capable of rendering realistic images. Besides image data, additional label information, such as depth, normal maps and object components masks, are generated. Hierarchical nature of generated labels corresponds to hierarchical representations which we want to be captured by the neural network. Such labels enable training of deep models in a compositional manner. This leads to the better understanding of the internal representations of the models and acceleration of the learning procedure. The framework allows users to render arbitrary scenes and objects according to their specific domain.
Czech name
—
Czech description
—

Publication year
2018
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Data Science and Knowledge Engineering for Sensing Decision Support
ISBN
9789813273221
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
1440-1445
Publisher name
World Scientific
Place of publication
Singapur
Event location
Belfast
Event date
Aug 21, 2018
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)