GEPC: Group-Equivariant Posterior Consistency for Out-of-Distribution Detection in Diffusion Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Rouzoumka, Yadang Alexis, Pinsolle, Jean, Terreaux, Eugénie, Morisseau, Christèle, Ovarlez, Jean-Philippe, Ren, Chengfang
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918343513997312
author Rouzoumka, Yadang Alexis
Pinsolle, Jean
Terreaux, Eugénie
Morisseau, Christèle
Ovarlez, Jean-Philippe
Ren, Chengfang
author_facet Rouzoumka, Yadang Alexis
Pinsolle, Jean
Terreaux, Eugénie
Morisseau, Christèle
Ovarlez, Jean-Philippe
Ren, Chengfang
contents Diffusion models learn a time-indexed score field $\mathbf{s}_θ(\mathbf{x}_t,t)$ that often inherits approximate equivariances (flips, rotations, circular shifts) from in-distribution (ID) data and convolutional backbones. Most diffusion-based out-of-distribution (OOD) detectors exploit score magnitude or local geometry (energies, curvature, covariance spectra) and largely ignore equivariances. We introduce Group-Equivariant Posterior Consistency (GEPC), a training-free probe that measures how consistently the learned score transforms under a finite group $\mathcal{G}$, detecting equivariance breaking even when score magnitude remains unchanged. At the population level, we propose the ideal GEPC residual, which averages an equivariance-residual functional over $\mathcal{G}$, and we derive ID upper bounds and OOD lower bounds under mild assumptions. GEPC requires only score evaluations and produces interpretable equivariance-breaking maps. On OOD image benchmark datasets, we show that GEPC achieves competitive or improved AUROC compared to recent diffusion-based baselines while remaining computationally lightweight. On high-resolution synthetic aperture radar imagery where OOD corresponds to targets or anomalies in clutter, GEPC yields strong target-background separation and visually interpretable equivariance-breaking maps. Code is available at https://github.com/RouzAY/gepc-diffusion/.
format Preprint
id arxiv_https___arxiv_org_abs_2602_00191
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GEPC: Group-Equivariant Posterior Consistency for Out-of-Distribution Detection in Diffusion Models
Rouzoumka, Yadang Alexis
Pinsolle, Jean
Terreaux, Eugénie
Morisseau, Christèle
Ovarlez, Jean-Philippe
Ren, Chengfang
Machine Learning
Computer Vision and Pattern Recognition
Diffusion models learn a time-indexed score field $\mathbf{s}_θ(\mathbf{x}_t,t)$ that often inherits approximate equivariances (flips, rotations, circular shifts) from in-distribution (ID) data and convolutional backbones. Most diffusion-based out-of-distribution (OOD) detectors exploit score magnitude or local geometry (energies, curvature, covariance spectra) and largely ignore equivariances. We introduce Group-Equivariant Posterior Consistency (GEPC), a training-free probe that measures how consistently the learned score transforms under a finite group $\mathcal{G}$, detecting equivariance breaking even when score magnitude remains unchanged. At the population level, we propose the ideal GEPC residual, which averages an equivariance-residual functional over $\mathcal{G}$, and we derive ID upper bounds and OOD lower bounds under mild assumptions. GEPC requires only score evaluations and produces interpretable equivariance-breaking maps. On OOD image benchmark datasets, we show that GEPC achieves competitive or improved AUROC compared to recent diffusion-based baselines while remaining computationally lightweight. On high-resolution synthetic aperture radar imagery where OOD corresponds to targets or anomalies in clutter, GEPC yields strong target-background separation and visually interpretable equivariance-breaking maps. Code is available at https://github.com/RouzAY/gepc-diffusion/.
title GEPC: Group-Equivariant Posterior Consistency for Out-of-Distribution Detection in Diffusion Models
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.00191