prikaz prve stranice dokumenta Duboki generativni modeli temeljeni na prostornom rasporedu dijelova slike
No public access
master's thesis
Duboki generativni modeli temeljeni na prostornom rasporedu dijelova slike
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2017. urn:nbn:hr:168:305338
Folnović, Matija
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Folnović, M. (2017). Duboki generativni modeli temeljeni na prostornom rasporedu dijelova slike (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:305338

Folnović, Matija. "Duboki generativni modeli temeljeni na prostornom rasporedu dijelova slike." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2017. https://urn.nsk.hr/urn:nbn:hr:168:305338

Folnović, Matija. "Duboki generativni modeli temeljeni na prostornom rasporedu dijelova slike." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2017. https://urn.nsk.hr/urn:nbn:hr:168:305338

Folnović, M. (2017). 'Duboki generativni modeli temeljeni na prostornom rasporedu dijelova slike', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 09 May 2024, https://urn.nsk.hr/urn:nbn:hr:168:305338

Folnović M. Duboki generativni modeli temeljeni na prostornom rasporedu dijelova slike [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2017 [cited 2024 May 09] Available at: https://urn.nsk.hr/urn:nbn:hr:168:305338

M. Folnović, "Duboki generativni modeli temeljeni na prostornom rasporedu dijelova slike", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2017. Available at: https://urn.nsk.hr/urn:nbn:hr:168:305338

Metadata
TitleDuboki generativni modeli temeljeni na prostornom rasporedu dijelova slike
Title (english)Deep generative models based on spatial layout of image parts
AuthorMatija Folnović
MentorSiniša Šegvić (mentor)
Committee memberSiniša Šegvić (predsjednik povjerenstva)
Committee memberMarin Golub (član povjerenstva)
Committee memberLeonardo Jelenković (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2017-07-20, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Iako moderni duboki modeli raspoznaju slike bolje od ljudi, problem klasifikacije slika još ne možemo smatrati riješenim. Poznato je da su duboki modeli skloni precijeniti pouzdanost predikcije, što može dovesti do vrlo neugodnih pogrešaka. Taj problem može se umanjiti primjenom reprezentacija koje sadrže prostorni raspored dijelova slike. Konkretno, prenaučenost se može umanjiti korištenjem regularizatora koji prisiljava model da nauči rekonstruirati ulaznu sliku. Ova ideja je proučavana kroz objavljen model koji se zove Duboki Što-Gdje Autoenkoder (engl. Stacked What-Where Autoencoder). Istražujemo prednosti i mane ovog pristupa u kontekstu polunadzirane klasifikacije jednostavnih slika i prikazujemo eksperimentalne rezultate na skupu MNIST.
Abstract (english)
Although modern deep models classify images better than humans, image classification cannot be regarded as a solved problem yet. It's known that deep models tend to overestimate prediction accuracy, which can lead to unpleasent errors. This problem can be reduced by exploiting representations containing spatial layout of image parts. In particular, overfitting can be reduced by supplying a regularizer which forces the model to be able to reconstruct the input image. This idea has been studied in the previously published model known as Stacked What-Where Autoencoder. We research advantages and disadvantages of this approach in regards to semi-supervised classification of simple images and present experimental results on the MNIST dataset.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:305338
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 on2019-03-13 20:15:42