English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
Add to Basket
 DetailsSummary
  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

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-002D-9345-9 Version Permalink: https://hdl.handle.net/11858/00-001M-0000-002D-9346-7
Genre: Thesis

Files

show Files

Locators

show
hide
Locator:
http://scidok.sulb.uni-saarland.de/volltexte/2017/6909/ (Any fulltext)
Description:
-
OA-Status:
Green
Locator:
http://scidok.sulb.uni-saarland.de/doku/lic_ohne_pod.php?la=de (Copyright transfer agreement)
Description:
-
OA-Status:
Not specified

Creators

show
hide
 Creators:
Lapin, Maksim1, 2, Author           
Schiele, Bernt1, Advisor           
Hein, Matthias3, Referee
Lampert, Christoph3, Referee
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              

Content

show
hide
Free keywords: -
 Abstract: 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

show
hide
Language(s): eng - English
 Dates: 2017-05-2220172017
 Publication Status: Issued
 Pages: 227 p.
 Publishing info: Saarbrücken : Universität des Saarlandes
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: Lapinphd17
URN: urn:nbn:de:bsz:291-scidok-69098
 Degree: PhD

Event

show

Legal Case

show

Project information

show

Source

show