prikaz prve stranice dokumenta Duboko učenje prijenosom znanja za segmentaciju slojeva retine
No public access
master's thesis
Duboko učenje prijenosom znanja za segmentaciju slojeva retine
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. urn:nbn:hr:168:423396
Hranić, Josip
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Hranić, J. (2020). Duboko učenje prijenosom znanja za segmentaciju slojeva retine (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:423396

Hranić, Josip. "Duboko učenje prijenosom znanja za segmentaciju slojeva retine." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:423396

Hranić, Josip. "Duboko učenje prijenosom znanja za segmentaciju slojeva retine." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:423396

Hranić, J. (2020). 'Duboko učenje prijenosom znanja za segmentaciju slojeva retine', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 04 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:423396

Hranić J. Duboko učenje prijenosom znanja za segmentaciju slojeva retine [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2020 [cited 2024 November 04] Available at: https://urn.nsk.hr/urn:nbn:hr:168:423396

J. Hranić, "Duboko učenje prijenosom znanja za segmentaciju slojeva retine", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:168:423396

Metadata
TitleDuboko učenje prijenosom znanja za segmentaciju slojeva retine
Title (english)Deep Transfer Learning for Retinal Layer Segmentation
AuthorJosip Hranić
MentorSven Lončarić (mentor)
Committee memberSven Lončarić (predsjednik povjerenstva)
Committee memberMarko Subašić (član povjerenstva)
Committee memberTomislav Petković (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2020-07-14, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Rad opisuje učenje modela konvolucijske neuronske mreže za segmentaciju slojeva retine. Analizirane su koristi i nedostaci prijenosa učenja i augmentacije podataka za semantičku segmentaciju. Kombinacija augmentacije podataka i prijenosa znanja omogućila je bolje rezultate istog modela obučenog od početka. Ovo je zaista važan rezultat, jer ogromni računski resursi nisu unutar svačijih mogućnosti, pogotovo kada se radi o velikim biomedicinskim skupovima podataka.
Abstract (english)
The paper describes the learning of a convolutional neural network model for retinal layer segmentation. The benefits and disadvantages of transfer learning and data augmentation for semantic segmentation are analyzed. The combination of data augmentation and transfer learning enabled better results of the same model trained from scratch. This is a really important result, because huge computing resources are not within everyone's capabilities, especially when it comes to large biomedical datasets.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:423396
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 10:03:27