AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

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

Marc Lafon, Elias Ramzi, Clément Rambour, Nicolas THOME

ICML 2023 · Label-efficient and robust learning › OOD and anomaly detection · approach: Provable and feature-based OOD detection · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add a learned residual EBM to GMM (ablation)GMM prior scorer · CIFAR-10, average OOD setsFPR95: 35.1 -> 31.5Improved
Add a learned residual EBM to GMM (ablation)GMM prior scorer · CIFAR-100, average OOD setsFPR95: 66.2 -> 64.9Improved
Add a learned residual EBM to EL (ablation)EL prior scorer · CIFAR-10, average OOD setsFPR95: 32.6 -> 31.0Improved
Add a learned residual EBM to EL (ablation)EL prior scorer · CIFAR-100, average OOD setsFPR95: 74.3 -> 72.6Improved
Train a residual EBM over a GMM prior rather than use a fully data-driven EBM (ablation)OOD density estimation · CIFAR-10, average OOD setsAUC: 93.3 -> 93.8Improved
Train a residual EBM over a GMM prior rather than use a fully data-driven EBM (ablation)OOD density estimation · CIFAR-100, average OOD setsAUC: 79.5 -> 82.1Improved
Compose corrected GMM and std-pooled GMM energies (ablation)HEAT · CIFAR-10, average OOD setsFPR95: 31.5 -> 25.6Improved
Compose corrected GMM and std-pooled GMM energies (ablation)HEAT · CIFAR-100, average OOD setsAUC: 82.1 -> 82.7Improved
Compose corrected GMM, std-pooled GMM, and EL energies (ablation)HEAT · CIFAR-10, average OOD setsFPR95: 31.5 -> 23.5Improved
Compose corrected GMM, std-pooled GMM, and EL energies (ablation)HEAT · CIFAR-100, average OOD setsAUC: 82.1 -> 83.0Improved
Use HEAT instead of SSD+OOD detection · CIFAR-10, average OOD setsFPR95: 35.1 -> 23.5Improved
Use HEAT instead of DICEOOD detection · ImageNet, average OOD setsAUC: 90.9 -> 92.6Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy