AI Paper Atlas

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

MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learning

Ylli Sadikaj, Hongkuan Zhou, Lavdim Halilaj, Stefan Schmid, Steffen Staab, Claudia Plant

ICCV 2025 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly detection · 14 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 KBA defect-aware prompts (ablation)MultiADS · MTAS MVTec-AD -> VisApixel AUROC: 87.0 -> 93.6Improved
add KBA defect-aware prompts (ablation)MultiADS · MTAS MVTec-AD -> MAD-simpixel AP: 26.5 -> 31.5Improved
use 4 feature stages instead of 3 (ablation)MultiADS · ZSAD MVTec-AD -> VisAimage AP: 82.3 -> 86.9Improved
add KBA prompts to ZSAD (ablation)MultiADS · ZSAD MVTec-AD -> VisAimage AP: 86.1 -> 86.9Improved
add global anomaly score a_x (ablation)MultiADS · ZSAD MVTec-AD -> VisAimage AP: 85.8 -> 86.9Improved
add KBA prompts to ZSAD on MPDD (ablation)MultiADS · ZSAD MVTec-AD -> MPDDimage AP: 77.6 -> 78.4 AP; AUROC 77.9 -> 78.3Mixed
filter product-irrelevant defect types at inference (MultiADS-F) (ablation)MultiADS · MPDD / MAD-real / Real-IAD ZSADimage AUROC: MPDD 78.3 -> 79.7; Real-IAD 78.7 -> 78.2Mixed
train on seen-defect-type data vs unseen defect typesMultiADS · MTAS VisA, trained on MVTec-ADpixel F1-score / AP: Hole AP 25.19 vs Extra AP 0.15Mixed
train on MVTec-AD or Real-IAD instead of MPDD to target VisAMultiADS · MTAS VisApixel AP: 23.3 -> 24.8Improved

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