On the Learnability of Out-of-distribution Detection

arXiv:2404.04865v1 Announce Type: new
Abstract: Supervised learning aims to train a classifier under the assumption that training and test data are from the same distribution. To ease the above assumption, researchers have studied a more realistic setting: out-of-distribution (OOD) detection, where test data may come from classes that are unknown during training (i.e., OOD data). Due to the unavailability and diversity of OOD data, good generalization ability is crucial for effective OOD detection algorithms, and corresponding learning theory is still …

abstract arxiv classifier cs.cv cs.lg data detection distribution researchers stat.ml supervised learning test train training type