izpis_h1_title_alt

Destilacija znanja globokih modelov za biometrijo beločnice
ID Bizjak, Matic (Author), ID Peer, Peter (Mentor) More about this mentor... This link opens in a new window, ID Štruc, Vitomir (Comentor), ID Vitek, Matej (Comentor)

.pdfPDF - Presentation file, Download (21,08 MB)
MD5: 011BC553CB21B2BCECB71D3E632A8CB4

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.

Language:Slovenian
Keywords:destilacija znanja, rezanje filtrov, konvolucijske nevronse mreže, beločnica, segmentacija
Work type:Master's thesis/paper
Typology:2.09 - Master's Thesis
Organization:FRI - Faculty of Computer and Information Science
Year:2020
PID:20.500.12556/RUL-121899 This link opens in a new window
COBISS.SI-ID:37218051 This link opens in a new window
Publication date in RUL:06.11.2020
Views:1105
Downloads:179
Metadata:XML DC-XML DC-RDF
:
Copy citation
Share:Bookmark and Share

Secondary language

Language:English
Title:Knowledge distillation of deep learning models for sclera biometrics
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.

Keywords:knowledge distillation, filter pruning, convolutional neural networks, sclera, segmentation

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Back