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.