prikaz prve stranice dokumenta Eksperimentalno vrednovanje metoda za monokularnu predikciju dubine
No public access
master's thesis
Eksperimentalno vrednovanje metoda za monokularnu predikciju dubine
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. urn:nbn:hr:168:009938
Špiljak, Dominik
University of Zagreb
Faculty of Electrical Engineering and Computing

Cite this document

Špiljak, D. (2022). Eksperimentalno vrednovanje metoda za monokularnu predikciju dubine (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:009938

Špiljak, Dominik. "Eksperimentalno vrednovanje metoda za monokularnu predikciju dubine." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. https://urn.nsk.hr/urn:nbn:hr:168:009938

Špiljak, Dominik. "Eksperimentalno vrednovanje metoda za monokularnu predikciju dubine." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. https://urn.nsk.hr/urn:nbn:hr:168:009938

Špiljak, D. (2022). 'Eksperimentalno vrednovanje metoda za monokularnu predikciju dubine', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 07 February 2025, https://urn.nsk.hr/urn:nbn:hr:168:009938

Špiljak D. Eksperimentalno vrednovanje metoda za monokularnu predikciju dubine [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2022 [cited 2025 February 07] Available at: https://urn.nsk.hr/urn:nbn:hr:168:009938

D. Špiljak, "Eksperimentalno vrednovanje metoda za monokularnu predikciju dubine", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:168:009938

Please login to the repository to save this object to your list.
Metadata
TitleEksperimentalno vrednovanje metoda za monokularnu predikciju dubine
Title (english)Experimental evaluation of methods for monocular depth prediction
AuthorDominik Špiljak
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 country2022-07-13, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Do nedavno, konvolucijski modeli su dominirali područjem računalnog vida koristeći preskočne veze i U-net strukturu. U području obrade prirodnog jezika je predstavljen transformer, model koji se temelji na mehanizmu pažnje te ostvaruje state-of-the-art rezultate. U području računalnog vida, inspiriran transformer modelom, predstavljen je vision transformer model koji ostvaruje state-of-the-art rezultate tom području. Najveći nedostaci modela koji se temelje na mehanizmu pažnje su potreba za vrlo velikom količinom podataka kako bi postigli maksimalne performanse te veliki memorijski otisak tijekom učenja. Kroz zadatak monokularne predikcije dubine, uspored̄uju se dvije vrste konvolucijskih modela, MIMO-Unet i LadderDenseNet, te jedan model koji se temelji na mehanizmu pažnje, DPT-Hybrid. Modeli su trenirani na podskupu NYU Depth V2 skupa podataka koji se sastoji od 50000 parova RGB slika i dubinskih mapa za treniranje te 654 parova za testiranje. U radu se uspoređuju vrijednosti 8 različitih metrika za performanse modela na testnom skupu te brzine zaključivanja i memorijski otisak svakog od modela.
Abstract (english)
Until recently, convolutional models dominated the field of computer visions using residual connections and U-net structure. In the field of natural language processing, a transformer, model based on the attention mechanism, was introduced and achieved state-of-the-art results. In the field of computer vision, inspired by the transformer model, a vision transformer model was presented that achieves state-of-the-art results in that field. The biggest disadvantages of attention-based models are the need for a very large amount of data to achieve maximum performance and big memory footprint during training. Through the task of monocular depth estimation, two types of convolutional models are compared, MIMO-Unet and LadderDenseNet, and one attention-based model, DPT-Hybrid. The models were trained on a subset of the NYU Depth V2 dataset consisting of 50000 pairs of RGB images and depth maps for training and 654 pairs for testing. This thesis compares the values of 8 different metrics for the performance of models on the test set and the speed of inference and memory footprint for each of the models.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:009938
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
RepositoryFER Repository
Created on2023-01-14 10:05:18

(©) Nacionalna i sveučilišna knjižnica u Zagrebu 2015. Sva prava pridržana. | Hrvatske bratske zajednice 4 p.p. 550, 10000 Zagreb, Hrvatska Tel. ++ 385 1 616-4040
OIB: 84838770814 | IBAN: HR66 2340 0091 1000 1008 1, Porezni broj (PDV identifikacijski broj) - VAT Number: HR84838770814
Prijava u repozitorij