Zero and Few Shot Learning With Semantic Feature Synthesis and Competitive Learning

Zero-shot learning (ZSL) is made possible by a projection function between feature space and semantic (e.g., an attribute space). Key to ZSL thus learn that robust against the often large domain gap seen unseen class domains. In this work, achieved data synthesis learning. Specifically, novel strategy proposed, which prototypes vectors) are used simply perturb for generating ones. As in any synthesis/hallucination approach, there ambiguities uncertainties on how well synthesised can capture targeted distribution. To cope with this, second contribution of work model termed competitive bidirectional (BPL) designed best utilise ambiguous data. we assume each point belong class; most likely two candidates exploited fashion. third contribution, show proposed be easily extended few-shot (FSL) again exploiting (class prototype guided) BPL. Extensive experiments our achieves state-of-the-art results both problems.