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

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

Keywords: Normalizing Flows, Out-of-Distribution Detection, Robotic Introspection

TL;DR: We propose to equip NFs with efficient but flexible base distributions to overcome the topological constraint for OOD detection in robot learning.

Abstract: 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 naı̈ve 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.

Student First Author: yes

Instructions: I have read the instructions for authors (https://corl2023.org/instructions-for-authors/)

Code: https://github.com/DLR-RM