Showing 2023Show all
2 papers · 1 filter
cs.RO2023
Topology-Matching Normalizing Flows for Out-of-Distribution Detection in Robot Learning
Jianxiang Feng, Jongseok Lee, Simon Geisler +2
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 detectio…
cs.LG2023
Learning Expressive Priors for Generalization and Uncertainty Estimation in Neural Networks
Dominik Schnaus, Jongseok Lee, Daniel Cremers +1
In this work, we propose a novel prior learning method for advancing generalization and uncertainty estimation in deep neural networks. The key idea is to exploit scalable and stru…