Topology-Matching Normalizing Flows for Out-of-Distribution Detection in Robot Learning
This work addresses out-of-distribution detection for autonomous robots, which is crucial for reliable real-world deployments, but it appears incremental as it builds on existing normalizing flow methods.
The paper tackles the problem of topological mismatch in normalizing flows for out-of-distribution detection in robot learning by using an expressive class-conditional base distribution, resulting in superior performance in density estimation and 2D object detection benchmarks and real-robot deployment.
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 naive 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.