Saved in:
Bibliographic Details
Main Authors: Yahiaoui, Mohamed Bahi, Daniel, Geoffrey, Giraldi, Loïc, Bruyelle, Jérémie, Arbel, Julyan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.22660
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918406060507136
author Yahiaoui, Mohamed Bahi
Daniel, Geoffrey
Giraldi, Loïc
Bruyelle, Jérémie
Arbel, Julyan
author_facet Yahiaoui, Mohamed Bahi
Daniel, Geoffrey
Giraldi, Loïc
Bruyelle, Jérémie
Arbel, Julyan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_22660
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Bounding Box Anomaly Scoring for simple and efficient Out-of-Distribution detection
Yahiaoui, Mohamed Bahi
Daniel, Geoffrey
Giraldi, Loïc
Bruyelle, Jérémie
Arbel, Julyan
Machine Learning
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.
title Bounding Box Anomaly Scoring for simple and efficient Out-of-Distribution detection
topic Machine Learning
url https://arxiv.org/abs/2603.22660