Enhancing Out-of-Distribution Detection with Multitesting-based Layer-wise Feature Fusion

arXiv:2403.10803v1 Announce Type: new
Abstract: Deploying machine learning in open environments presents the challenge of encountering diverse test inputs that differ significantly from the training data. These out-of-distribution samples may exhibit shifts in local or global features compared to the training distribution. The machine learning (ML) community has responded with a number of methods aimed at distinguishing anomalous inputs from original training data. However, the majority of previous studies have primarily focused on the output layer or penultimate layer of …

abstract arxiv challenge community cs.ai cs.cv cs.lg data detection distribution diverse environments feature features fusion global inputs layer machine machine learning responded samples test training training data type wise