InFlow: Robust outlier detection utilizing Normalizing Flows

10 Jun 2021  ·  Nishant Kumar, Pia Hanfeld, Michael Hecht, Michael Bussmann, Stefan Gumhold, Nico Hoffmann ·

Normalizing flows are prominent deep generative models that provide tractable probability distributions and efficient density estimation. However, they are well known to fail while detecting Out-of-Distribution (OOD) inputs as they directly encode the local features of the input representations in their latent space. In this paper, we solve this overconfidence issue of normalizing flows by demonstrating that flows, if extended by an attention mechanism, can reliably detect outliers including adversarial attacks. Our approach does not require outlier data for training and we showcase the efficiency of our method for OOD detection by reporting state-of-the-art performance in diverse experimental settings. Code available at https://github.com/ComputationalRadiationPhysics/InFlow .

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods