AI Paper Atlas

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

PIRN: Prototypical-based Intra-modal Reconstruction with Normality Communication for Multi-modal Anomaly Detection.

YITING LI, Xulei Yang, Jing Zhang, Sichao Tian, Jingyi Liao, Fayao Liu

ICLR 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly 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
add Balanced Prototype Assignment (ablation)PIRN · MVTec-3D-AD (10-shot)image AUROC: 0.883 -> 0.922Improved
add Adaptive Prototype Refinement (ablation)PIRN · MVTec-3D-AD (10-shot)image AUROC: 0.916 -> 0.922Improved
add Multimodal Normality Communication (ablation)PIRN · MVTec-3D-AD (10-shot)image AUROC: 0.867 -> 0.922Improved
add surface normals to RGB (ablation)PIRN · MVTec-3D-AD (10-shot)image AUROC: 0.827 -> 0.922Improved
use surface normals instead of RGB alone (ablation)PIRN · MVTec-3D-AD (10-shot)image AUROC: 0.827 -> 0.879Improved
use balanced OT instead of global averaging for APR aggregation (ablation)PIRN · MVTec-3D-AD (10-shot)image AUROC: 0.915 -> 0.922Improved
use balanced OT instead of top-k averaging (ablation)PIRN · MVTec-3D-AD (10-shot)image AUROC: 0.921 -> 0.922No clear effect
increase prototypes from 10 to 100 (ablation)PIRN · MVTec-3D-AD (all-shot)image AUROC: 0.963 -> 0.901Hurt
reduce prototypes from 10 to 5 (ablation)PIRN · MVTec-3D-AD (all-shot)image AUROC: 0.963 -> 0.954Hurt
increase decoder layers from 2 to 8 (ablation)PIRN · MVTec-3D-AD (10-shot)image AUROC: 0.924 -> 0.869Hurt
use PIRN instead of INP-FormerINP-Former · MVTec-3D-AD (5-shot)image AUROC: 0.851 -> 0.890Improved
use PIRN instead of FIND in computeFIND · MVTec-3D-AD (10-shot)FLOPs: 728.46 -> 103.36 GFLOPsImproved

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