Using Neural Network Formalism to Solve Multiple-Instance Problems

Many objects in the real world are difficult to describe by means of a single numerical vector of a fixed length, whereas describing them by means of a set of vectors is more natural. Therefore, Multiple instance learning (MIL) techniques have been constantly gaining in importance throughout the last years. MIL formalism assumes that each object (sample) is represented by a set (bag) of feature vectors (instances) of fixed length, where knowledge about objects (e.g., class label) is available on bag level but not necessarily on instance level. Many standard tools including supervised classifiers have been already adapted to MIL setting since the problem got formalized in the late nineties. In this work we propose a neural network (NN) based formalism that intuitively bridges the gap between MIL problem definition and the vast existing knowledge-base of standard models and classifiers. We show that the proposed NN formalism is effectively optimizable by a back-propagation algorithm and can reveal unknown patterns inside bags. Comparison to 14 types of classifiers from the prior art on a set of 20 publicly available benchmark datasets confirms the advantages and accuracy of the proposed solution.