Hybrid Energy Based Model in the Feature Space for Out-of-Distribution Detection - Laboratoire Traitement et Communication de l'Information Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

Hybrid Energy Based Model in the Feature Space for Out-of-Distribution Detection

Résumé

Out-of-distribution (OOD) detection is a critical requirement for the deployment of deep neural networks. This paper introduces the HEAT model, a new post-hoc OOD detection method estimating the density of in-distribution (ID) samples using hybrid energy-based models (EBM) in the feature space of a pre-trained backbone. HEAT complements prior density estimators of the ID density, e.g. parametric models like the Gaussian Mixture Model (GMM), to provide an accurate yet robust density estimation. A second contribution is to leverage the EBM framework to provide a unified density estimation and to compose several energy terms. Extensive experiments demonstrate the significance of the two contributions. HEAT sets new state-of-the-art OOD detection results on the CIFAR-10 / CIFAR-100 benchmark as well as on the large-scale Imagenet benchmark. The code is available at: https://github.com/MarcLafon/heatood.
Fichier principal
Vignette du fichier
ICML23_HybridEnergy_OOD (2).pdf (9.58 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04112184 , version 1 (31-05-2023)
hal-04112184 , version 2 (06-06-2023)

Identifiants

Citer

Marc Lafon, Elias Ramzi, Clément Rambour, Nicolas Thome. Hybrid Energy Based Model in the Feature Space for Out-of-Distribution Detection. 2023. ⟨hal-04112184v1⟩
195 Consultations
118 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More