Feedback

Faculté des Sciences appliquées
Faculté des Sciences appliquées
MASTER THESIS
VIEW 35 | DOWNLOAD 1

Master Thesis : Semi-Supervised Learning For Computer Vision

Download
Makedonsky, Aliocha ULiège
Promotor(s) : Geurts, Pierre ULiège ; Nath Ranga, Rakesh ULiège
Date of defense : 26-Jun-2023/27-Jun-2023 • Permalink : http://hdl.handle.net/2268.2/17721
Details
Title : Master Thesis : Semi-Supervised Learning For Computer Vision
Translated title : [fr] Apprentissage semi-supervisé pour vision par ordinateur
Author : Makedonsky, Aliocha ULiège
Date of defense  : 26-Jun-2023/27-Jun-2023
Advisor(s) : Geurts, Pierre ULiège
Nath Ranga, Rakesh ULiège
Committee's member(s) : Louppe, Gilles ULiège
Wehenkel, Louis ULiège
Language : English
Number of pages : 85
Keywords : [en] semi-supervised learning
[en] machine learning
[en] computer vision
[en] imbalance
Discipline(s) : Engineering, computing & technology > Computer science
Target public : Professionals of domain
Student
Institution(s) : Université de Liège, Liège, Belgique
Degree: Master : ingénieur civil en science des données, à finalité spécialisée
Faculty: Master thesis of the Faculté des Sciences appliquées

Abstract

[en] When working on real-world projects, the dataset might contain few labeled samples and much more unlabeled samples. The purpose of this thesis is to explore techniques that would leverage unlabeled data to improve the results of a model that would have been trained only in the few labeled samples.


File(s)

Document(s)

File
Access s171197Makedonsky2023.pdf
Description: -
Size: 9.18 MB
Format: Adobe PDF

Annexe(s)

File
Access s171197Makedonsky2023.zip
Description: -
Size: 925.56 kB
Format: Unknown

Author

  • Makedonsky, Aliocha ULiège Université de Liège > Master ingé. civ. sc. don. à . fin.

Promotor(s)

Committee's member(s)

  • Louppe, Gilles ULiège Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Big Data
    ORBi View his publications on ORBi
  • Wehenkel, Louis ULiège Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Méthodes stochastiques
    ORBi View his publications on ORBi
  • Total number of views 35
  • Total number of downloads 1










All documents available on MatheO are protected by copyright and subject to the usual rules for fair use.
The University of Liège does not guarantee the scientific quality of these students' works or the accuracy of all the information they contain.