Mahalanobis-Aware Training for Out-of-Distribution Detection
DOI:
https://doi.org/10.1609/aaaiss.v2i1.27681Keywords:
Machine Learning (ML), Reliability, Safety, Computer Vision (CV)Abstract
While deep learning models have seen widespread success in controlled environments, there are still barriers to their adoption in open-world settings. One critical task for safe deployment is the detection of anomalous or out-of-distribution samples that may require human intervention. In this work, we present a novel loss function and recipe for training networks with improved density-based out-of-distribution sensitivity. We demonstrate the effectiveness of our method on CIFAR-10, notably reducing the false-positive rate of the relative Mahalanobis distance method on far-OOD tasks by over 50%.Downloads
Published
2024-01-22
Issue
Section
Assured and Trustworthy Human-centered AI (ATHAI)