Publikation
Cross-Modal Learning Of Visual Categories Using Different Levels of Supervision
M. Fritz; Geert-Jan Kruijff; B. Schiele
In: Proceedings of the International Conference on Computer Vision Systems (ICVS 2007). International Conference on Computer Vision Systems (ICVS), Bielefeld, Germany, ICVS, 3/2007.
Zusammenfassung
Today’s ob ject categorization methods use either supervised
or unsupervised training methods. While supervised methods tend to
produce more accurate results, unsupervised methods are highly attrac-
tive due to their potential to use far more and unlabeled training data.
This paper proposes a novel method that uses unsupervised training to
obtain visual groupings of ob jects and a cross-modal learning scheme
to overcome inherent limitations of purely unsupervised training. The
method uses a unified and scale-invariant ob ject representation that al-
lows to handle labeled as well as unlabeled information in a coherent
way. One of the potential settings is to learn ob ject category models
from many unlabeled observations and a few dialogue interactions that
can be ambiguous or even erroneous. First experiments demonstrate the
ability of the system to learn meaningful generalizations across ob jects
already from a few dialogue interactions.