Novel Ensemble Diversification Methods for Open-Set Scenarios

Abstract

We revisit existing ensemble diversification approaches and present two novel diversification methods tailored for open-set scenarios. The first method uses a new loss, designed to encourage models disagreement on outliers only, thus alleviating the intrinsic accuracy-diversity trade-off. The second method achieves diversity via automated feature engineering, by training each model to disregard input features learned by previously trained ensemble models. We conduct an extensive evaluation and analysis of the proposed techniques on seven datasets that cover image classification, re-identification and recognition domains. We compare to and demonstrate accuracy improvements over the existing state-of-the-art ensemble diversification methods.