AI Paper Atlas

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

Fisher-Rao Sensitivity for Out-of-Distribution Detection in Deep Neural Networks

Anthony Nguyen, Antonin Bertrand, Sylvie Le Hégarat-Mascle, Emanuel Aldea, Mohammed Nabil EL-KORSO, Renaud LUSTRAT, Franck FLORIN

ICLR 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Uncertainty and misclassification detection

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
use additive product-manifold score instead of multiplicative Standard FIM Trace (ablation)FIM Trace · ImageNet-O (ViT-B/16)AUROC: 89.03 -> 92.61Improved
use additive score instead of multiplicative Standard FIM Trace (ablation)FIM Trace · ImageNet-O (ResNet-50)AUROC: 61.11 -> 71.77Improved
use additive score instead of multiplicative Standard FIM Trace (ablation)FIM Trace · CIFAR-10 vs SVHN (ResNet-18)AUROC: 86.16 -> 91.28Improved
use additive score instead of Tensor FIM Trace (ablation)FIM Trace · ImageNet-O (ViT-B/16)AUROC: 90.12 -> 92.61Improved
add tensor-subspace projection to Standard FIM Trace (ablation)FIM Trace · ImageNet-O (ResNet-50)AUROC: 61.11 -> 65.23Improved
use LDA instead of PCA for feature subspace (ablation)Additive FIM Trace · ImageNet-1K OoD (ResNet-50)AUROC combined: 76.73 -> 82.93Improved
use LDA subspace instead of no projection (ablation)Additive FIM Trace · ImageNet-1K OoD (ResNet-50)AUROC combined: 78.16 -> 82.93Improved
use LDA instead of PCA for residual signal (ablation)Residual score · ImageNet-1K OoD (ResNet-50)AUROC residual: 58.92 -> 80.23Improved
increase calibration set from 1,500 to 50,000 samples (ablation)Additive FIM Trace · ImageNet-1K OoD (ResNet-50)AUROC combined: 76.04 -> 82.97Improved
increase calibration set from 10,000 to 50,000 samples (ablation)Additive FIM Trace · ImageNet-1K OoD (ResNet-50)AUROC combined: 82.21 -> 82.97No clear effect
use Additive FIM Trace instead of ViMAdditive FIM Trace · ImageNet-O (ResNet-50)AUROC: 68.21 -> 71.77Improved
use Additive FIM Trace instead of ViMAdditive FIM Trace · Places365 (ViT-B/16)AUROC: 90.83 -> 89.51Hurt

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