Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
 
 
DownloadE-Mail
 DetailsÜbersicht
  Image Classification with Limited Training Data and Class Ambiguity

Lapin, M. (2017). Image Classification with Limited Training Data and Class Ambiguity. PhD Thesis, Universität des Saarlandes, Saarbrücken.

Item is

 

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:
Datensatz-Permalink: https://hdl.handle.net/11858/00-001M-0000-002D-9345-9 Versions-Permalink: https://hdl.handle.net/11858/00-001M-0000-002D-9346-7
Genre: Hochschulschrift

Externe Referenzen

einblenden:
ausblenden:
externe Referenz:
http://scidok.sulb.uni-saarland.de/volltexte/2017/6909/ (beliebiger Volltext)
Beschreibung:
-
OA-Status:
Grün
externe Referenz:
http://scidok.sulb.uni-saarland.de/doku/lic_ohne_pod.php?la=de (Verlagsvertrag)
Beschreibung:
-
OA-Status:
Keine Angabe

Urheber

einblenden:
ausblenden:
 Urheber:
Lapin, Maksim1, 2, Autor           
Schiele, Bernt1, Ratgeber           
Hein, Matthias3, Gutachter
Lampert, Christoph3, 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: Modern image classification methods are based on supervised learning algorithms that require labeled training data. However, only a limited amount of annotated data may be available in certain applications due to scarcity of the data itself or high costs associated with human annotation. Introduction of additional information and structural constraints can help improve the performance of a learning algorithm. In this thesis, we study the framework of learning using privileged information and demonstrate its relation to learning with instance weights. We also consider multitask feature learning and develop an efficient dual optimization scheme that is particularly well suited to problems with high dimensional image descriptors. Scaling annotation to a large number of image categories leads to the problem of class ambiguity where clear distinction between the classes is no longer possible. Many real world images are naturally multilabel yet the existing annotation might only contain a single label. In this thesis, we propose and analyze a number of loss functions that allow for a certain tolerance in top k predictions of a learner. Our results indicate consistent improvements over the standard loss functions that put more penalty on the first incorrect prediction compared to the proposed losses. All proposed learning methods are complemented with efficient optimization schemes that are based on stochastic dual coordinate ascent for convex problems and on gradient descent for nonconvex formulations.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 2017-05-2220172017
 Publikationsstatus: Erschienen
 Seiten: 227 p.
 Ort, Verlag, Ausgabe: Saarbrücken : Universität des Saarlandes
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: BibTex Citekey: Lapinphd17
URN: urn:nbn:de:bsz:291-scidok-69098
 Art des Abschluß: Doktorarbeit

Veranstaltung

einblenden:

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle

einblenden: