prikaz prve stranice dokumenta Gusta predikcija primjenom slojeva pažnje
No public access
master's thesis
Gusta predikcija primjenom slojeva pažnje
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. urn:nbn:hr:168:060616
Pleše, Leo
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Pleše, L. (2022). Gusta predikcija primjenom slojeva pažnje (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:060616

Pleše, Leo. "Gusta predikcija primjenom slojeva pažnje." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. https://urn.nsk.hr/urn:nbn:hr:168:060616

Pleše, Leo. "Gusta predikcija primjenom slojeva pažnje." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. https://urn.nsk.hr/urn:nbn:hr:168:060616

Pleše, L. (2022). 'Gusta predikcija primjenom slojeva pažnje', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 22 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:060616

Pleše L. Gusta predikcija primjenom slojeva pažnje [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2022 [cited 2024 November 22] Available at: https://urn.nsk.hr/urn:nbn:hr:168:060616

L. Pleše, "Gusta predikcija primjenom slojeva pažnje", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:168:060616

Metadata
TitleGusta predikcija primjenom slojeva pažnje
Title (english)Dense prediction by means of self-attention layers
AuthorLeo Pleše
MentorSiniša Šegvić (mentor)
Committee memberSiniša Šegvić (predsjednik povjerenstva)
Committee memberMarko Čupić (član povjerenstva)
Committee memberJan Šnajder (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2022-07-14, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Gusta predikcija složen je izazov u računalnom vidu koji, uz konvolucijske modele, sve više rješavaju i transformeri. Motivirani time analiziramo generalizacijsku moć u gustoj predikciji i vremensko-prostornu učinkovitost transformera i konvolucijskih modela. Od transformera za gustu predikciju odabiremo Segmenter i SWIN, a za konvolucijski model primarno piramidalni SwiftNet. Inicijalno učenje Segmentera na PASCAL Contextu indiciralo je generalizacijsku moć Segmentera. Pokazali smo na Cityscapesu da su transformeri i konvolucijski modeli usporedive točnosti, no da su transformeri zahtjevniji za učenje. Na ADE20k smo otkrili da je djelomično naučen SWIN-T bolje točnosti od Segmenter-Ti i na Cityscapesu da nevalidiran SWIN-B bolje generalizira od Segmenter-B. Isprobali smo na Cityscapesu nekoliko ansambala i združenih modela SwiftNet-ResNet18-p i Segmenter-Ti kako bismo dobili model bolje točnosti od zasebnih modela. Ansambli su u tome uspjeli, a združeni modeli nisu. Vjerujemo da bi se iscrpnom validacijom našli združeni modeli koji bi premašili točnost ansambala.
Abstract (english)
Dense prediction is a complex challenge in computer vision that, besides convolutional models, is increasingly being solved by transformers. Motivated by this, we analyze the generalization power in dense prediction and the spatio-temporal efficiency of transformers and convolutional models. From transformers for dense prediction we choose Segmenter and SWIN, and for convolutional model primarily pyramidal SwiftNet. The initial learning of Segmenters on PASCAL Context indicated generalization power of Segmenters. We showed on Cityscapes that transformers and convolutional models are of comparable accuracy but transformers are more demanding to learn. On ADE20K we found that the partially learned SWIN-T had better accuracy than Segmenter-Ti and on Cityscapes that the unvalidated SWIN-B generalizes better than Segmenter-B. We tested couple ensembles and joint models of SwiftNet-ResNet18-p and Segmenter-Ti on Cityscapes so as to get a model of better accuracy than individual models. The ensembles succeeded in this but the joint models did not. We believe that by exhaustive validation joint models which would exceed ensembles' accuracy could be found.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:060616
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 15:54:16