Artykuł w czasopiśmie
Brak miniatury
Licencja
Toward Machine Learning on Granulated Data – a Case of Compact Autoencoder-based Representations of Satellite Images
cris.lastimport.scopus | 2024-02-12T19:01:55Z |
dc.abstract.en | We consider a problem of learning from compact representations of images for a purpose of object recognition and content-based image retrieval. We discuss a motivation for using compressed images in those tasks and indicate exemplary applications related to analysis on the data from satellites. Finally, we show some preliminary results of experiments conducted to demonstrate the impact of the image data granulation on the quality of classification. We empirically compare the performance of prediction models trained on original images, images compressed using autoencoders, and on images whose quality was lowered in order to reduce their size. |
dc.affiliation | Uniwersytet Warszawski |
dc.conference.country | Stany Zjednoczone |
dc.conference.datefinish | 2018-12-13 |
dc.conference.datestart | 2018-12-10 |
dc.conference.place | Seattle |
dc.conference.series | IEEE International Conference on Big Data |
dc.conference.series | IEEE International Conference on Big Data |
dc.conference.seriesshortcut | BigData |
dc.conference.shortcut | IEEE BigData 2018 |
dc.contributor.author | Grad, Łukasz |
dc.contributor.author | Ślęzak, Dominik |
dc.contributor.author | Przyborowski, Mateusz |
dc.contributor.author | Janusz, Andrzej |
dc.contributor.author | Tajmajer, Tomasz |
dc.contributor.author | Biczyk, Piotr |
dc.date.accessioned | 2024-01-26T11:04:07Z |
dc.date.available | 2024-01-26T11:04:07Z |
dc.date.issued | 2018 |
dc.description.finance | Nie dotyczy |
dc.identifier.doi | 10.1109/BIGDATA.2018.8622562 |
dc.identifier.uri | https://repozytorium.uw.edu.pl//handle/item/123580 |
dc.identifier.weblink | https://ieeexplore.ieee.org/document/8622562/authors#authors |
dc.language | eng |
dc.pbn.affiliation | computer and information sciences |
dc.relation.pages | 2657 - 2662 |
dc.rights | ClosedAccess |
dc.sciencecloud | nosend |
dc.subject.en | Image coding |
dc.subject.en | Satellites |
dc.subject.en | Task analysis |
dc.subject.en | Machine learning |
dc.subject.en | Decoding |
dc.subject.en | Image retrieval |
dc.subject.en | Semantics |
dc.title | Toward Machine Learning on Granulated Data – a Case of Compact Autoencoder-based Representations of Satellite Images |
dc.type | JournalArticle |
dspace.entity.type | Publication |