Research

Multiple Instance Learning (MIL) generally represents each example as a collection of instances such that the features for local objects can be better captured, whereas traditional methods typically extract a global feature vector for each example as an integral part. However, there is limited research work on investigating which of the two learning scenarios performs better.

This paper proposes a novel framework – Multiple Instance LEArning with Global Embedding (MILEAGE), in which the global feature vectors for traditional learning methods are integrated into the MIL setting. Within the proposed framework, a large margin method is formulated to adaptively tune the weights on the two different kinds of feature representations (i.e., global and multiple instance) for each example and trains the classifier simultaneously.

An extensive set of experiments are conducted to demonstrate the advantages of the proposed method.