AI Paper Atlas

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

Unified Multi-Layer Subspace Modeling for Cross-Domain OOD Detection

Gerhard Krumpl, Henning Avenhaus, Horst Possegger

ECCV 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 0 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
fuse shallow-to-deep layers then model once (PRISM) vs MDS++penultimate-layer Mahalanobis OOD · Average AUROC over 3 benchmarksAUROC: 89.13 -> 93.92Improved
add residual energy term to projected Mahalanobis term (ablation)PRISM · Average of 3 benchmarksAUROC: 92.19 -> 93.47Improved
add residual energy term to projected Mahalanobis term (ablation)PRISM · Average of 3 benchmarksFPR95: 29.00 -> 23.65Improved
add projected Mahalanobis term to residual energy term (ablation)PRISM · OpenOOD ImageNet-1kAUROC: 76.39 -> 89.88Improved
add projected Mahalanobis term to residual energy term (ablation)PRISM · OpenMIBOODAUROC: 95.72 -> 94.86Hurt
add residual energy term to projected Mahalanobis term (ablation)PRISM · OpenOOD ImageNet-1kAUROC: 89.94 -> 89.88No clear effect
PCA dimension 128 vs 512 (ablation)PRISM · Average of 3 benchmarksAUROC: 93.11 -> 93.47No clear effect
PCA dimension 768 vs 512 (ablation)PRISM · Average of 3 benchmarksAUROC: 93.04 -> 93.47No clear effect
multiplicative instead of additive score fusion (ablation)PRISM · score combinationAUROCImproved
OOD-calibrated layer aggregation (MDSEns) vs ID-onlyMDSEns · OpenOOD ImageNet-1kAUROC: 89.83 -> 54.41Hurt
PRISM vs MDS++ on Swin-TPRISM · ImageNet-1k Swin-TAUROC: 88.85 -> 90.91Improved
PRISM vs MDS++ on ViT-B/16PRISM · ImageNet-1k ViT-B/16AUROC: 89.52 -> 88.76Hurt

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