A boosting approach to multiple instance learning
This is the latest version of this eprint.
In this paper we present a boosting approach to multiple-instance learning. As weak hypotheses we use balls (with respect to various metrics) centered at instances of positive bags. For the metric induced by the infinity-norm these hypotheses can be modified into hyper-rectangles by a greedy algorithm. Compared to other approaches our algorithm delivers improved or at least competitive results on several multiple-instance benchmark data sets.
Available Versions of this Item