prikaz prve stranice dokumenta Kontrastno učenje modela za prevođenje slika
No public access
undergraduate thesis
Kontrastno učenje modela za prevođenje slika
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. urn:nbn:hr:168:878648
Spiegl, Bernard
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Spiegl, B. (2021). Kontrastno učenje modela za prevođenje slika (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:878648

Spiegl, Bernard. "Kontrastno učenje modela za prevođenje slika." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. https://urn.nsk.hr/urn:nbn:hr:168:878648

Spiegl, Bernard. "Kontrastno učenje modela za prevođenje slika." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. https://urn.nsk.hr/urn:nbn:hr:168:878648

Spiegl, B. (2021). 'Kontrastno učenje modela za prevođenje slika', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 23 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:878648

Spiegl B. Kontrastno učenje modela za prevođenje slika [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2021 [cited 2024 November 23] Available at: https://urn.nsk.hr/urn:nbn:hr:168:878648

B. Spiegl, "Kontrastno učenje modela za prevođenje slika", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:168:878648

Metadata
TitleKontrastno učenje modela za prevođenje slika
Title (english)Contrastive learning for image-to-image translation
AuthorBernard Spiegl
MentorSiniša Šegvić (mentor)
Committee memberSiniša Šegvić (predsjednik povjerenstva)
Committee memberJosip Šarić (član povjerenstva)
Committee memberIvan Grubišić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2021-07-08, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Modeli za prevođenje slika pretvaraju sliku iz izvorne domene u odredišnu domenu i pri tome nastoje sačuvati sadržaj slike. Metoda s kontrastivnim učenjem jedan je od pristupa za rješavanje ovakvog tipa problema. Prednost ove metode je što omogućuje treniranje u slučaju kada je domena samo jedna slika. Ono što ju razlikuje od prethodnika je činjenica da koristi isječke slika prilikom treniranja umjesto cijelih slika. Također je pokazano da uzimanje negativa (isječci slike potrebni za izračunavanje gubitka) iz iste slike postiže bolje rezultate nego kad se negativi uzimaju iz drugih slika u datasetu. Ovakav pristup potiče mapiranje odgovarajućih isječaka na približno isto mjesto u odnosu na druge isječke (negative) dok istovremeno poboljšava kvalitetu rezultirajuće slike i smanjuje vrijeme potrebno za treniranje u odnosu na baseline metode: CycleGAN, MUNIT, DRIT, DistanceGAN, SelfDistance i GCGAN.
Abstract (english)
Image-to-image translation models transfer images from input domain to output domain in an endeavour to retain the content of the image. Contrastive Unpaired Translation is one of the existing methods for solving such problems. Significant advantage of this method, compared to competitors, is the ability to train and perform well in cases where both input and output domains are only a single image. Another key thing that differentiates this method from its predecessors is the usage of image patches rather than whole images. It also turns out that sampling negatives (patches required to calculate loss) from the same image achieves better results than a scenario where the negatives are sampled from other images in the dataset. This type of approach encourages mapping of corresponding patches to the same location in relation to other patches (negatives) while at the same time both improves the output image quality and significantly decreases the time required to train the model compared to other baseline methods such as CycleGAN, MUNIT, DRIT, DistanceGAN, SelfDistance and GCGAN.
Keywords
Keywords (english)
Languageenglish
URN:NBNurn:nbn:hr:168:878648
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 on2023-01-14 21:40:23