Print
Univis
Search
 
FAU-Logo
Techn. Fakultät Willkommen am Institut für Informatik FAU-Logo

Seminar Unsupervised Learning in Vision [SemULV]

Dates
First date: 17.10.13, 18h c.t., Room 01.151 (Martensstr. 3)

Seminar: upon agreement
Slides
  • Summary
    In Computer Vision we often facing the problem of missing labels of data.

    Unsupervised learning offers the possibility to detect structure in data without class labels. The data can be grouped to clusters, or a data driven representation can be learnt.

    In this seminar we focus on the following methods to cope with these problems:

    • Clustering and visualization with self-organizing maps (SOM)
    • Clustering and segmentation with mean shift
    • Classification with bag of words approaches

    Every participant will develop a prototype, based on current publications. The performed experiments for the individual task are then presented to the group and summarized in a short report.
Examples
Clustering over a trained SOM
Colored presentation of the found clusters