Exploring Vicinal Risk Minimization for Lightweight Out-of-Distribution Detection

Understand

Deep neural networks have found widespread adoption in solving complex tasks ranging from image recognition to natural language processing.

• However, these networks make confident mispredictions when presented with data that does not belong to the training distribution, i.e.
• out-of-distribution (OoD) samples.
• In this paper we explore whether the property of Vicinal Risk Minimization (VRM) to smoothly interpolate between different class boundaries helps to train better OoD detectors.