AI Paper Atlas

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

Bidirectional Multimodal Prompt Learning with Scale-Aware Training for Few-Shot Multi-Class Anomaly Detection

Yujin Lee, Sewon Kim, Daeun Moon, Seoyoon Jang, Hyunsoo Yoon

CVPR 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly detection · 7 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 bidirectional text-image prompt coupling (ablation)AnoPLe · MVTec-AD / VisA / Real-IAD 1-shotimage AUROC: 93.0/90.3 -> 94.5 on MVTec-ADImproved
add one-way I->T coupling instead of bidirectional (ablation)AnoPLe · MVTec-AD 1-shotimage AUROC: 94.5 -> 91.2Hurt
add alignment loss between local and global features (ablation)AnoPLe · Real-IAD 1-shotimage AUROC: 73.3 -> 81.2Improved
use weighted-sum alignment instead of mean alignment (ablation)AnoPLe · Real-IAD 1-shotimage AUROC: 74.2 -> 81.2Improved
add multi-scale training (ablation)AnoPLe · MVTec-AD 1-shotimage AUROC: 89.9 -> 91.8Improved
add scale-aware prefix on top of multi-scale training (ablation)AnoPLe · MVTec-AD 1-shotimage AUROC: 91.8 -> 94.5Improved
use class name instead of generic [object] token (ablation)AnoPLe · Real-IAD 1-shotimage AUROC: 76.0 -> 81.2Improved
remove anomaly descriptions from PromptAD prompt pool (ablation)PromptAD · MVTec-AD screwimage AUROC: 55.7 -> 44.7Hurt
hold out one class during training (AnoPLe vs INP-Former)AnoPLe · MVTec-AD held-outimage AUROC: INP-Former 67.7 vs AnoPLe 87.5Improved
AnoPLe vs vision-only INP-Former on all-seen 4-shotAnoPLe · Real-IAD 4-shotimage AUROC: 88.3 vs 83.2Hurt
apply AnoPLe to medical anomaly detection without adaptationAnoPLe · BMAD Brain MRI 4-shotimage AUROC: UniVAD 82.6 vs AnoPLe 79.8Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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