Subspace Modeling for Fast Out-Of-Distribution and Anomaly Detection

TL;DR

This paper introduces a fast, low-cost subspace modeling technique using linear and kernel methods on deep neural network features for effective out-of-distribution and anomaly detection.

Contribution

It proposes a novel feature reconstruction error approach with linear and kernel methods for efficient OOD and anomaly detection in DNNs.

Findings

Outperforms or matches state-of-the-art detection methods

Requires significantly less computational and memory resources

Effective across various datasets and neural network architectures

Abstract

This paper presents a fast, principled approach for detecting anomalous and out-of-distribution (OOD) samples in deep neural networks (DNN). We propose the application of linear statistical dimensionality reduction techniques on the semantic features produced by a DNN, in order to capture the low-dimensional subspace truly spanned by said features. We show that the "feature reconstruction error" (FRE), which is the $\ell_2$-norm of the difference between the original feature in the high-dimensional space and the pre-image of its low-dimensional reduced embedding, is highly effective for OOD and anomaly detection. To generalize to intermediate features produced at any given layer, we extend the methodology by applying nonlinear kernel-based methods. Experiments using standard image datasets and DNN architectures demonstrate that our method meets or exceeds best-in-class quality performance, but at a fraction of the computational and memory cost required by the state of the art. It can be trained and run very efficiently, even on a traditional CPU.