Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
 
 
DownloadE-Mail
 DetailsÜbersicht
  Semi-supervised Learning for Image Classification

Ebert, S. (2012). Semi-supervised Learning for Image Classification. PhD Thesis, Universität des Saarlandes, Saarbrücken.

Item is

 

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:
Datensatz-Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-F787-B Versions-Permalink: https://hdl.handle.net/11858/00-001M-0000-0028-14A8-2
Genre: Hochschulschrift

Externe Referenzen

einblenden:
ausblenden:
externe Referenz:
http://scidok.sulb.uni-saarland.de/volltexte/2013/5265/ (beliebiger Volltext)
Beschreibung:
-
OA-Status:
Grün

Urheber

einblenden:
ausblenden:
 Urheber:
Ebert, Sandra1, 2, Autor           
Schiele, Bernt1, Ratgeber           
Bischof, Horst3, Gutachter
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              
2International Max Planck Research School, MPI for Informatics, Max Planck Society, Campus E1 4, 66123 Saarbrücken, DE, ou_1116551              
3External Organizations, ou_persistent22              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: Object class recognition is an active topic in computer vision still presenting many challenges. In most approaches, this task is addressed by supervised learning algorithms that need a large quantity of labels to perform well. This leads either to small datasets (< 10,000 images) that capture only a subset of the real-world class distribution (but with a controlled and verified labeling procedure), or to large datasets that are more representative but also add more label noise. Therefore, semi-supervised learning is a promising direction. It requires only few labels while simultaneously making use of the vast amount of images available today. We address object class recognition with semi-supervised learning. These algorithms depend on the underlying structure given by the data, the image description, and the similarity measure, and the quality of the labels. This insight leads to the main research questions of this thesis: Is the structure given by labeled and unlabeled data more important than the algorithm itself? Can we improve this neighborhood structure by a better similarity metric or with more representative unlabeled data? Is there a connection between the quality of labels and the overall performance and how can we get more representative labels? We answer all these questions, i.e., we provide an extensive evaluation, we propose several graph improvements, and we introduce a novel active learning framework to get more representative labels.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 2012-12-142013-04-262012
 Publikationsstatus: Erschienen
 Seiten: XI, 163 p.
 Ort, Verlag, Ausgabe: Saarbrücken : Universität des Saarlandes
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: BibTex Citekey: EbertDiss2012
Anderer: A876B5595E818773C1257B19003EA758-EbertDiss2012
URN: urn:nbn:de:bsz:291-scidok-52659
 Art des Abschluß: Doktorarbeit

Veranstaltung

einblenden:

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle

einblenden: