magistrsko delo
Matic Bizjak (Author), Peter Peer (Mentor), Vitomir Štruc (Co-mentor), Matej Vitek (Co-mentor)

Abstract

Destilacija znanja je pristop izdelave lahkih modelov s prenosom znanja iz globokih modelov, ki imajo veliko število parametrov, so časovno zahtevni in imajo zelo visoko natančnost. V magistrskem delu ovrednotimo pristop destilacije znanja na področju biometrije očesa. Izdelamo nov postopek pridobitve lahkega modela za segmentacijo beločnice s kombinacijo dveh pristopov, destilacije znanja in rezanja filtrov, ter pokažemo, da sta oba pristopa ključna za uspeh našega postopka. S predstavljenim izvirnim postopkom pridobitve lahkega modela odstranimo 74 % operacij s plavajočo vejico za eno sklepanje in 73,2 % parametrov ter izgubimo 1,27 % natančnosti, poleg tega pa odstranimo 2-krat toliko parametrov kot najsodobnejši model in v primerjavi izgubimo le 1,74 % natančnosti. V luči te primerjave na koncu identificiramo možne nadgradnje, ki imajo potencial za izboljšanje našega pristopa.

Keywords

destilacija znanja;rezanje filtrov;konvolucijske nevronse mreže;beločnica;segmentacija;računalništvo;računalništvo in informatika;magisteriji;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UL FRI - Faculty of Computer and Information Science
Publisher: [M. Bizjak]
UDC: 004.93:57.087.1(043.2)
COBISS: 37218051 Link will open in a new window
Views: 766
Downloads: 130
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Knowledge distillation of deep learning models for sclera biometrics
Secondary abstract: Knowledge distillation is a technique for the development of lightweight models by transferring knowledge from a deep model with high memory footprint and high computational complexity. In this work we evaluate knowledge distillation for eye biometrics. We propose a new algorithm for creating a lightweight model for sclera segmentation by combining knowledge distillation with filter pruning and show that both techniques are key to achieving good results. With the presented algorithm we remove 74% floating point operations needed for one inference and 73.2% parameters and sacrifice 1.27% of the accuracy. In addition, we remove twice as many parameters as the current state-of-the-art filter pruning approach and in comparison sacrifice 1.74% of the accuracy. In the light of this comparison, we identify possible improvements that have a potential to further increase the accuracy of our algorithm.
Secondary keywords: knowledge distillation;filter pruning;convolutional neural networks;sclera;segmentation;computer science;computer and information science;master's degree;
Type (COBISS): Master's thesis/paper
Study programme: 1000471
Embargo end date (OpenAIRE): 1970-01-01
Thesis comment: Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages: 53 str.
ID: 12133081