ロボット学習における分布外検出のためのトポロジー整合正規化フロー
Topology-Matching Normalizing Flows for Out-of-Distribution Detection in Robot Learning
正規化フローの基底分布を情報理論的目的で学習し、複雑な対象分布のトポロジーに整合させることで、ロボット学習における分布外検出精度を向上させた研究。
著者: Jianxiang Feng, Jongseok Lee, Simon Geisler, Stephan Gunnemann, Rudolph Triebel
分類: cs.RO, cs.LG
原文アブストラクト
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.
