prikaz prve stranice dokumenta Osjetljivost semantičke segmentacije na pomak domene
No public access
undergraduate thesis
Osjetljivost semantičke segmentacije na pomak domene
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. urn:nbn:hr:168:871467
Antunović, Željko
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Antunović, Ž. (2023). Osjetljivost semantičke segmentacije na pomak domene (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:871467

Antunović, Željko. "Osjetljivost semantičke segmentacije na pomak domene." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:871467

Antunović, Željko. "Osjetljivost semantičke segmentacije na pomak domene." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:871467

Antunović, Ž. (2023). 'Osjetljivost semantičke segmentacije na pomak domene', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 26 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:871467

Antunović Ž. Osjetljivost semantičke segmentacije na pomak domene [Undergraduate 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:168:871467

Ž. Antunović, "Osjetljivost semantičke segmentacije na pomak domene", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:168:871467

Metadata
TitleOsjetljivost semantičke segmentacije na pomak domene
Title (english)Sensitivity of semantic segmentation to domain shift
AuthorŽeljko Antunović
MentorSiniša Šegvić (mentor)
Committee memberSiniša Šegvić (predsjednik povjerenstva)
Committee memberJosip Šarić (član povjerenstva)
Committee memberMarin Kačan (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2023-07-06, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Današnji modeli za semantičku segmentaciju postižu vrlo dobre rezultate na određenim podatcima, no pomak domene je i dalje neriješen problem u računalnom vidu. U ovome radu proučavamo posljedice pomaka domene u kontekstu sintetičkih podatka te koje su koristi i mane u korištenju sintetičkih podataka. U radu su opisani glavni pojmovi u području dubokog učenja relevantnih za ovu tematiku poput neuronskih mreža, konvolucijskih i semantičkih modela. Također je opisano poopćenje domene, prilagođavanje domene i pojam prijenosnog učenja kao bitne pojmove u kontekstu pomaka domene. Korišteni podatci su GTA i Cityscapes, a arhitektura je SwiftNet s ResNet-18 okosnicom. Kod je napisan u programskom jeziku Python 3 koristeći biblioteke NumPy i PyTorch. Cijeli kod je pokrenut preko platforme Kaggle koja omogućava pokretanje koda na GPU jedinicama.
Abstract (english)
State of the art semantic segmentation models perform very well on specific datasets, but domain shift is still an unresolved problem in computer vision. In this paper we observe the effects of domain shift in a specific case of synthetic data and we discuss both the pros and cons of using said data for training semantic segmentation models. The paper goes over the basics of deep learning relevant to the context, such as neural networks, convolutional and semantic segmentation models. Furthermore, the paper also goes over domain generalization, domain adaptation and transfer learning as important concepts in relation to domain shift. Datasets used in this paper are GTA and Cityscapes, while the used architecture is SwiftNet with a ResNet-18 backbone. The code was written in Python 3 using NumPy and PyTorch libraries. The whole project was run on the Kaggle platform, which allows users to run their Python code on powerful GPUs.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:871467
Study programmeTitle: Computing
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2023-07-13 09:52:25