Saved in:
Bibliographic Details
Main Authors: Huang, Zhexiao, He, Weihao, Deng, Shutao, Chen, Junzhe, Yuan, Chao, Wang, Hongxin, Zhou, Changsheng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.00849
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915592260288512
author Huang, Zhexiao
He, Weihao
Deng, Shutao
Chen, Junzhe
Yuan, Chao
Wang, Hongxin
Zhou, Changsheng
author_facet Huang, Zhexiao
He, Weihao
Deng, Shutao
Chen, Junzhe
Yuan, Chao
Wang, Hongxin
Zhou, Changsheng
contents Out-of-distribution (OOD) detection is essential for deploying deep learning models in open-world environments. Existing approaches, such as energy-based scoring and gradient-projection methods, typically rely on high-dimensional representations to separate in-distribution (ID) and OOD samples. We introduce P-OCS (Perturbations in the Orthogonal Complement Subspace), a lightweight and theoretically grounded method that operates in the orthogonal complement of the principal subspace defined by ID features. P-OCS applies a single projected perturbation restricted to this complementary subspace, enhancing subtle ID-OOD distinctions while preserving the geometry of ID representations. We show that a one-step update is sufficient in the small-perturbation regime and provide convergence guarantees for the resulting detection score. Experiments across multiple architectures and datasets demonstrate that P-OCS achieves state-of-the-art OOD detection with negligible computational cost and without requiring model retraining, access to OOD data, or changes to model architecture.
format Preprint
id arxiv_https___arxiv_org_abs_2511_00849
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Perturbations in the Orthogonal Complement Subspace for Efficient Out-of-Distribution Detection
Huang, Zhexiao
He, Weihao
Deng, Shutao
Chen, Junzhe
Yuan, Chao
Wang, Hongxin
Zhou, Changsheng
Machine Learning
Out-of-distribution (OOD) detection is essential for deploying deep learning models in open-world environments. Existing approaches, such as energy-based scoring and gradient-projection methods, typically rely on high-dimensional representations to separate in-distribution (ID) and OOD samples. We introduce P-OCS (Perturbations in the Orthogonal Complement Subspace), a lightweight and theoretically grounded method that operates in the orthogonal complement of the principal subspace defined by ID features. P-OCS applies a single projected perturbation restricted to this complementary subspace, enhancing subtle ID-OOD distinctions while preserving the geometry of ID representations. We show that a one-step update is sufficient in the small-perturbation regime and provide convergence guarantees for the resulting detection score. Experiments across multiple architectures and datasets demonstrate that P-OCS achieves state-of-the-art OOD detection with negligible computational cost and without requiring model retraining, access to OOD data, or changes to model architecture.
title Perturbations in the Orthogonal Complement Subspace for Efficient Out-of-Distribution Detection
topic Machine Learning
url https://arxiv.org/abs/2511.00849