Topology-Matching Normalizing Flows for Out-of-Distribution Detection in Robot Learning

Jianxiang Feng, Jongseok Lee, Simon Geisler, Stephan Günnemann, Rudolph Triebel

Research output: Contribution to journalConference articlepeer-review


To facilitate reliable deployments of autonomous robots in the real world, Out-of-Distribution (OOD) detection capabilities are often required. A powerful approach for OOD detection is based on density estimation with Normalizing Flows (NFs). However, we find that prior work with NFs attempts to match the complex target distribution topologically with naïve base distributions leading to adverse implications. In this work, we circumvent this topological mismatch using an expressive class-conditional base distribution trained with an information-theoretic objective to match the required topology. The proposed method enjoys the merits of wide compatibility with existing learned models without any performance degradation and minimum computation overhead while enhancing OOD detection capabilities. We demonstrate superior results in density estimation and 2D object detection benchmarks in comparison with extensive baselines. Moreover, we showcase the applicability of the method with a real-robot deployment.

Original languageEnglish
JournalProceedings of Machine Learning Research
StatePublished - 2023
Event7th Conference on Robot Learning, CoRL 2023 - Atlanta, United States
Duration: 6 Nov 20239 Nov 2023


  • Normalizing Flows
  • Out-of-Distribution
  • Robotic Introspection


Dive into the research topics of 'Topology-Matching Normalizing Flows for Out-of-Distribution Detection in Robot Learning'. Together they form a unique fingerprint.

Cite this