AI Paper Atlas

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

FEVER-OOD: Free Energy Vulnerability Elimination for Robust Out-of-Distribution Detection

Brian K.S. Isaac-Medina, Mauricio Che, Yona Falinie A. Gaus, Samet Akcay, Toby P. Breckon

ICCV 2025 · Label-efficient and robust learning › OOD and anomaly detection · approach: Provable and feature-based OOD detection · 3 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 null space reduction layer (96-NSR) plus LSV regulariser to VOS (ablation)VOS · CIFAR-10FPR95: 33.66 -> 28.22Improved
Add 96-NSR plus LSV regulariser to FFS (ablation)FFS · CIFAR-10AUROC: 90.52 -> 94.03Improved
Reduce features all the way to 10 dimensions (10-NSR) (ablation)VOS · CIFAR-10FPR95: 33.66 -> 37.61Hurt
Add LSV regulariser only (no NSR) to VOS (ablation)VOS · CIFAR-10FPR95: 33.66 -> 33.19No clear effect
Use condition number regulariser instead of LSV regulariser (ablation)VOS · CIFAR-10AUROC: 92.92 (LSVR) vs 91.98 (CNR)Hurt
Add 114-NSR plus LSV regulariser to VOS (ablation)VOS · CIFAR-100FPR95: 71.01 -> 68.57Improved
Add 100-NSR plus LSV regulariser to Dream-OOD (ablation)Dream-OOD · CIFAR-100FPR95: 50.96 -> 42.77Improved
Add 100-NSR plus LSV regulariser to Dream-OOD (ablation)Dream-OOD · ImageNet-100FPR95: 39.33 -> 36.50Improved
Add LSV regulariser to pretrained Dream-OOD without NSR layer (ablation)Dream-OOD · ImageNet-100FPR95: 39.33 -> 65.25Hurt
Use condition number regulariser with 100-NSR (ablation)VOS, FFS, Dream-OOD · CIFAR-100convergenceHurt
Add 768-NSR plus condition number regulariser to VOS detectorVOS (Faster R-CNN) · PASCAL VOC to MS-COCOFPR95: 50.29 -> 47.47Improved
Add FEVER-OOD to object detectorsVOS/FFS · PASCAL VOCmAP: 0.489 -> 0.491No clear effect

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