prikaz prve stranice dokumenta Polunadzirana semantička segmentacija utemeljena na pseudooznačavanju
No public access
master's thesis
Polunadzirana semantička segmentacija utemeljena na pseudooznačavanju
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. urn:nbn:hr:168:106671
Petrač, Toma
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Petrač, T. (2021). Polunadzirana semantička segmentacija utemeljena na pseudooznačavanju (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:106671

Petrač, Toma. "Polunadzirana semantička segmentacija utemeljena na pseudooznačavanju." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. https://urn.nsk.hr/urn:nbn:hr:168:106671

Petrač, Toma. "Polunadzirana semantička segmentacija utemeljena na pseudooznačavanju." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. https://urn.nsk.hr/urn:nbn:hr:168:106671

Petrač, T. (2021). 'Polunadzirana semantička segmentacija utemeljena na pseudooznačavanju', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 26 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:106671

Petrač T. Polunadzirana semantička segmentacija utemeljena na pseudooznačavanju [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2021 [cited 2024 December 26] Available at: https://urn.nsk.hr/urn:nbn:hr:168:106671

T. Petrač, "Polunadzirana semantička segmentacija utemeljena na pseudooznačavanju", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:168:106671

Metadata
TitlePolunadzirana semantička segmentacija utemeljena na pseudooznačavanju
Title (english)Semi-supervised semantic segmentation based on pseudolabelling
AuthorToma Petrač
MentorSiniša Šegvić (mentor)
Committee memberSiniša Šegvić (predsjednik povjerenstva)
Committee memberMarko Čupić (član povjerenstva)
Committee memberVladimir Čeperić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2021-07-16, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Semantička segmentacija prirodnih scena važan je zadatak računalnog vida s mnogim zanimljivim primjenama. Jako dobre rezultate na tom zadatku postižu konvolucijski modeli s lakom klasifikacijskom osnovom i ljestvičastim naduzorkovanjem. Ovaj rad bavi se polunadziranim učenjem takvih modela, što znači da model uči na grupama koje se sastoje od označenih i neoznačenih slika. Koristi se polunadzirana metoda pseudooznačavanja neoznačenih slika, najprije na manjem i jednostavnijem skupu podataka, a zatim na nešto kompleksnijem. Provedeno je mnogo iscrpnih eksperimenata koji su pokazali da metoda doista daje bolje rezultate nego uobičajeni postupak nadziranog učenja.
Abstract (english)
The segmentation of natural scenes is an important task of computer vision with many interesting applications. Very good results on this task are achieved by convolutional models with a light-weight general purpose architecture as the main recognition engine, and upsampling with lateral connections. This paper deals with the semi-supervised learning of such models, which means that the model learns in groups consisting of both labeled and unlabeled images. A semi-supervised method of pseudo-labeling is used, first on a smaller and simpler data set, and then on a somewhat more complex one. Many exhaustive experiments have been conducted which have shown that the method really gives better results than the usual supervised learning procedure.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:106671
Study programmeTitle: Computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2023-01-13 13:28:28