Bounding Box Anomaly Scoring for simple and efficient Out-of-Distribution detection

TL;DR

This paper introduces Bounding Box Anomaly Scoring (BBAS), a simple and efficient post-hoc method for out-of-distribution detection that uses bounding-box abstraction to improve robustness and representation flexibility.

Contribution

BBAS combines bounding-box abstraction with graded anomaly scores and multi-layer clustering, offering a novel, compact, and effective approach for OOD detection.

Findings

BBAS achieves robust separation between in- and out-of-distribution samples.

The method maintains simplicity and compactness of bounding-box representations.

Experimental results outperform existing post-hoc OOD detection methods.

Abstract

Out-of-distribution (OOD) detection aims to identify inputs that differ from the training distribution in order to reduce unreliable predictions by deep neural networks. Among post-hoc feature-space approaches, OOD detection is commonly performed by approximating the in-distribution support in the representation space of a pretrained network. Existing methods often reflect a trade-off between compact parametric models, such as Mahalanobis-based scores, and more flexible but reference-based methods, such as k-nearest neighbors. Bounding-box abstraction provides an attractive intermediate perspective by representing in-distribution support through compact axis-aligned summaries of hidden activations. In this paper, we introduce Bounding Box Anomaly Scoring (BBAS), a post-hoc OOD detection method that leverages bounding-box abstraction. BBAS combines graded anomaly scores based on interval exceedances, monitoring variables adapted to convolutional layers, and decoupled clustering and box construction for richer and multi-layer representations. Experiments on image-classification benchmarks show that BBAS provides robust separation between in-distribution and out-of-distribution samples while preserving the simplicity, compactness, and updateability of the bounding-box approach.