AI Paper Atlas

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

The Invisible Gorilla Effect in Out-of-distribution Detection

Harry Anthony, Ziyun Liang, Hermione Warr, Konstantinos Kamnitsas

CVPR 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Provable and feature-based 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
make OOD ink artefact dissimilar to lesion ROI colour (vs similar)Mahalanobis · ISIC inkAUROC (%): 76.98 -> 63.64Hurt
make OOD ink artefact dissimilar to lesion ROI colour (vs similar)KNN · ISIC inkAUROC (%): 85.68 -> 70.10Hurt
make OOD ink artefact dissimilar to lesion ROI colour (vs similar)FeatureNorm · ISIC inkAUROC (%): 75.12 -> 52.91Hurt
make OOD ink artefact dissimilar to lesion ROI colour (vs similar)DDPM-MSE · ISIC inkAUROC (%): 68.64 -> 70.85No clear effect
feature-based vs confidence-based methods: mean AUROC drop between similar and dissimilar artefactsfeature-based methods · ISIC real benchmarksmean AUROC drop (pp): 7.1 vs 1.5Hurt
train on hypointense-heart counterfactuals instead of hyperintense (ROI intensity flip) (ablation)Mahalanobis · CheXpert synthetic squaresAUROC drop (%): 6.31 -> 4.28 (preference reverses)Mixed
swap artefact colour with synthetic counterfactual (dissimilar) for colour chartsMahalanobis · ISIC colour chartsAUROC (%): 96.11 -> 93.77Hurt
add light colour jitter augmentation (ablation)KNN · ISIC inkAUROC (%) on dissimilar ink: 70.10 -> 77.3Improved
add colour jitter augmentation (ablation)DICE · ISIC inkAUROC (%) on similar ink: 69.04 -> 61.8Hurt
use heavy colour jitter instead of none (ablation)ResNet18 primary model · ISICID accuracy (pp): -5.5Hurt
add nuisance subspace projection (ablation)Mahalanobis · ISIC inkAUROC (%) on dissimilar ink: 63.6 -> 75.8Improved
add nuisance subspace projection (ablation)FeatureNorm · ISIC inkAUROC (%) on dissimilar ink: 52.9 -> 74.5Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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