DOC3-Deep One Class Classification using Contradictions

This paper introduces the notion of learning from contradictions (a.k.a Universum learning) for deep one class classification problems. We formalize this notion for the widely adopted one class large-margin loss (Sch¨olkopf et al., 2001), and propose the Deep One Class Classification using Contradictions (DOC 3 ) algorithm. We show that learning from contradictions incurs lower generalization error by comparing the Empirical Rademacher Complexity (ERC) of DOC 3 against its traditional inductive learning counterpart. Our empirical results demonstrate the ef-ficacy of DOC 3 compared to popular baseline algorithms on several real-life data sets.