prikaz prve stranice dokumenta Gusta detekcija anomalija generativnim modelima
No public access
master's thesis
Gusta detekcija anomalija generativnim modelima
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. urn:nbn:hr:168:143902
Delić, Anja
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Delić, A. (2023). Gusta detekcija anomalija generativnim modelima (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:143902

Delić, Anja. "Gusta detekcija anomalija generativnim modelima." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:143902

Delić, Anja. "Gusta detekcija anomalija generativnim modelima." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:143902

Delić, A. (2023). 'Gusta detekcija anomalija generativnim modelima', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 10 May 2024, https://urn.nsk.hr/urn:nbn:hr:168:143902

Delić A. Gusta detekcija anomalija generativnim modelima [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2023 [cited 2024 May 10] Available at: https://urn.nsk.hr/urn:nbn:hr:168:143902

A. Delić, "Gusta detekcija anomalija generativnim modelima", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:168:143902

Metadata
TitleGusta detekcija anomalija generativnim modelima
Title (english)Dense anomaly detection with generative models
AuthorAnja Delić
MentorSiniša Šegvić (mentor)
Committee memberSiniša Šegvić (predsjednik povjerenstva)
Committee memberZoran Kalafatić (član povjerenstva)
Committee memberLeonardo Jelenković (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2023-07-10, Croatia
Abstract
Standardni diskriminativni modeli za semantičku segmentaciju osjetljivi su na pojavu anomalija u ispitnim slikama. Navedeni problem rješavamo detekcijom anomalija razredom uvjetovanim normalizirajućim tokovima. Predlažemo mjere anomalnosti temeljene na teoriji informacije s probabilističkom interpretacijom te ih primjenjujemo na predikcije na razini piksela i maski. Predložena hibridna metoda postiže kompetitivne rezultate na standardnim testnim skupovima slika i poboljšanje u odnosu na usporedive diskriminativne metode za gustu detekciju anomalija.
Abstract (english)
Standard discriminative models for semantic segmentation are sensitive to the presence of anomalies in test images. We address this issue by detecting anomalies using class-conditional normalizing flows. We define anomaly scores based on information theory with probabilistic interpretation and apply them to pixel-level and mask-level predictions. The proposed hybrid method achieves competitive results on standard benchmarks and improvement upon comparable discriminative dense anomaly detection methods.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:143902
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 on2023-10-11 08:42:38