Semi-supervised Learning for Large Scale Image Cosegmentation

This paper introduces to use semi-supervised learning for large scale image co segmentation. Different from traditional unsupervised co segmentation that does not use any segmentation ground truth, semi-supervised co segmentation exploits the similarity from both the very limited training image fore...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	2013 IEEE International Conference on Computer Vision S. 393 - 400
Hauptverfasser:	Wang, Zhengxiang, Liu, Rujie
Format:	Tagungsbericht Journal Article
Sprache:	Englisch
Veröffentlicht:	IEEE 01.12.2013
Schlagworte:	Binary quadratic programming problem Computer vision Energy conservation Energy management Energy minimization function Ground truth Histograms Image cosegmentation Image segmentation Iterative algorithms Mathematical analysis Mathematical models Minimization Quadratic programming Segmentation Segments Semi-supervised learning Semisupervised learning Training Training data Vectors
ISSN:	1550-5499
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!