LGCVDec 24, 2022

Out-of-Distribution Detection with Reconstruction Error and Typicality-based Penalty

arXiv:2212.12641v117 citationsh-index: 16
Originality Incremental advance
AI Analysis

This work addresses the critical need for reliable OOD detection in real-world applications, offering an incremental improvement over existing typicality-based approaches.

The paper tackled the problem of out-of-distribution (OOD) detection in high dimensions by proposing a new method called penalized reconstruction error (PRE), which combines reconstruction error with a typicality-based penalty using normalizing flows, and demonstrated its effectiveness on natural image datasets like CIFAR-10, TinyImageNet, and ILSVRC2012.

The task of out-of-distribution (OOD) detection is vital to realize safe and reliable operation for real-world applications. After the failure of likelihood-based detection in high dimensions had been shown, approaches based on the \emph{typical set} have been attracting attention; however, they still have not achieved satisfactory performance. Beginning by presenting the failure case of the typicality-based approach, we propose a new reconstruction error-based approach that employs normalizing flow (NF). We further introduce a typicality-based penalty, and by incorporating it into the reconstruction error in NF, we propose a new OOD detection method, penalized reconstruction error (PRE). Because the PRE detects test inputs that lie off the in-distribution manifold, it effectively detects adversarial examples as well as OOD examples. We show the effectiveness of our method through the evaluation using natural image datasets, CIFAR-10, TinyImageNet, and ILSVRC2012.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes