prikaz prve stranice dokumenta Polunadzirano učenje segmentacijskih modela zasnovanih na pažnji
No public access
master's thesis
Polunadzirano učenje segmentacijskih modela zasnovanih na pažnji
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. urn:nbn:hr:168:837960
Škrabić, Matej
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Škrabić, M. (2023). Polunadzirano učenje segmentacijskih modela zasnovanih na pažnji (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:837960

Škrabić, Matej. "Polunadzirano učenje segmentacijskih modela zasnovanih na pažnji." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:837960

Škrabić, Matej. "Polunadzirano učenje segmentacijskih modela zasnovanih na pažnji." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:837960

Škrabić, M. (2023). 'Polunadzirano učenje segmentacijskih modela zasnovanih na pažnji', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 26 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:837960

Škrabić M. Polunadzirano učenje segmentacijskih modela zasnovanih na pažnji [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2023 [cited 2024 December 26] Available at: https://urn.nsk.hr/urn:nbn:hr:168:837960

M. Škrabić, "Polunadzirano učenje segmentacijskih modela zasnovanih na pažnji", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:168:837960

Metadata
TitlePolunadzirano učenje segmentacijskih modela zasnovanih na pažnji
Title (english)Semisupervised learning of segmentation models based on attention
AuthorMatej Škrabić
MentorMarko Čupić (mentor)
Committee memberMarko Čupić (predsjednik povjerenstva)
Committee memberSiniša Šegvić (član povjerenstva)
Committee memberŽeljka Mihajlović (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2023-09-14, Croatia
Abstract
U okviru rada predstavljeni su različiti pristupi za segmentaciju slike, uključujući tradicionalne algoritme, konvolucijske modele za semantičku segmentaciju i modele zasnovane na pažnji. Detaljno je opisana arhitektura odabranih modela: Transformer, Vision Transformer, Data-efficient Image Transformer i Segmenter. Kako bi se ublažila potreba za velikom količinom slika označenih na razini piksela, istražene su različite metode polunadziranog učenja s naglaskom na metode konzistencijskog učenja. Implementirana je metoda polunadziranog učenja temeljena na modelu učenik-učitelj uz fotometrijske perturbacije i upotrebu maskirajućeg autoenkodera te je iskorištena za učenje modela Segmenter na javno dostupnom skupu podataka CityScapes.
Abstract (english)
This thesis describes different image segmentation techniques, including traditional ad-hoc algorithms and machine learning approaches: convolutional and attention-based models. We described and explained the architecture of the following models: Transformer, Vision Transformer, Data-efficient Image Transformer and Segmenter. Semi-supervised training is utilized to tackle the problematic need for a large amount of pixel-wise labeled data in the context of semantic segmentation. Focus is placed on consistency regularization methods. We implemented a semi-supervised training procedure based on the student-teacher model with the use of photometric perturbations and token masking, and used it for training of the Segmenter model on the publicly available CityScapes dataset.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:837960
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 on2024-03-28 07:55:13