Critical Points ++: An Agile Point Cloud Importance Measure for Robust Classification, Adversarial Defense and Explainable AI. (arXiv:2308.05525v1 [cs.CV])

The ability to cope accurately and fast with Out-Of-Distribution (OOD)
samples is crucial in real-world safety demanding applications. In this work we
first study the interplay between critical points of 3D point clouds and OOD
samples. Our findings are that common corruptions and outliers are often
interpreted as critical points. We generalize the notion of critical points
into importance measures. We show that training a classification network based
only on less important points dramatically improves robustness, at a cost of …

agile applications arxiv classification cloud defense distribution explainable ai importance safety study work world