DeepAI AI Chat
Log In Sign Up

Why Normalizing Flows Fail to Detect Out-of-Distribution Data

by   Polina Kirichenko, et al.

Detecting out-of-distribution (OOD) data is crucial for robust machine learning systems. Normalizing flows are flexible deep generative models that often surprisingly fail to distinguish between in- and out-of-distribution data: a flow trained on pictures of clothing assigns higher likelihood to handwritten digits. We investigate why normalizing flows perform poorly for OOD detection. We demonstrate that flows learn local pixel correlations and generic image-to-latent-space transformations which are not specific to the target image dataset. We show that by modifying the architecture of flow coupling layers we can bias the flow towards learning the semantic structure of the target data, improving OOD detection. Our investigation reveals that properties that enable flows to generate high-fidelity images can have a detrimental effect on OOD detection.


page 20

page 21

page 23

page 24

page 26


InFlow: Robust outlier detection utilizing Normalizing Flows

Normalizing flows are prominent deep generative models that provide trac...

Normalizing flows for novelty detection in industrial time series data

Flow-based deep generative models learn data distributions by transformi...

Integrable Nonparametric Flows

We introduce a method for reconstructing an infinitesimal normalizing fl...

Whitening Convergence Rate of Coupling-based Normalizing Flows

Coupling-based normalizing flows (e.g. RealNVP) are a popular family of ...

Out-of-Distribution Detection of Melanoma using Normalizing Flows

Generative modelling has been a topic at the forefront of machine learni...

Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows

The detection of manufacturing errors is crucial in fabrication processe...

Woodbury Transformations for Deep Generative Flows

Normalizing flows are deep generative models that allow efficient likeli...

Code Repositories


Glow model implementation

view repo


Deep Generative Models that I have implemented, trained and experimented with.

view repo