Semi-supervised Multi-sensor Classification via Consensus-based Multi-View Maximum Entropy Discrimination
This addresses classification in multi-sensor systems where labeling is costly, but it appears incremental as it builds on existing multi-view learning frameworks.
The paper tackles multi-sensor classification with many unlabeled samples by proposing a consensus-based multi-view maximum entropy discrimination algorithm, which improves performance over previous multi-view learning approaches on three real datasets.
In this paper, we consider multi-sensor classification when there is a large number of unlabeled samples. The problem is formulated under the multi-view learning framework and a Consensus-based Multi-View Maximum Entropy Discrimination (CMV-MED) algorithm is proposed. By iteratively maximizing the stochastic agreement between multiple classifiers on the unlabeled dataset, the algorithm simultaneously learns multiple high accuracy classifiers. We demonstrate that our proposed method can yield improved performance over previous multi-view learning approaches by comparing performance on three real multi-sensor data sets.