AI Paper Atlas

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

Rethinking Continual Anomaly Detection on the Edge: Benchmarking Under Realistic Industrial Conditions

Chad Weatherly, Sen Lin

ECCV 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly 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
use DINOSaur (frozen DINOv3 + spatial coreset memory) instead of dedicated CAD methodsUCAD/DNE/IUF · MVTec-ADimage AUROC: 0.798 -> 0.968 (vs UCAD)Improved
DINOSaur vs PatchCore with replayPatchCore · MVTec-ADimage AUROC: 0.925 -> 0.968Improved
DINOSaur vs PatchCore with replayPatchCore · MVTec-LOCOimage AUROC: 0.743 -> 0.768Improved
dedicated CL mechanisms vs simple experience replay on traditional ADDNE, IUF, UCAD · MVTec-ADimage AUROC: PatchCore+replay 0.925 vs UCAD 0.798Hurt
replay for EfficientADEfficientAD · MVTec-ADimage AUROC: 0.529 (near chance)No clear effect
DINOSaur under geometric driftDINOSaur · MTD-Geoimage AUROC: 0.519 (chance)No clear effect
DINOSaur vs PatchCore on color driftPatchCore · MTD-Colorimage AUROC: 0.836 -> 0.928Improved
DINOSaur vs PatchCore latency on JetsonPatchCore · Jetson Orin Nanolatency ms: 119.0 -> 91.6Improved
increase coreset ratio from 10% to 20% (ablation)DINOSaur · Avg AUROC over 5 protocolsAUROC: 0.801 -> 0.816Improved
decrease coreset ratio from 10% to 1% (ablation)DINOSaur · Avg AUROC over 5 protocolsAUROC: 0.801 -> 0.780Hurt
increase neighborhood radius from 0 to 3 at rho=10% (ablation)DINOSaur · Avg AUROC over 5 protocolsAUROC: 0.787 -> 0.801Improved
pixel-level vs image-level evaluationall methods · MVTec-AD, LOCO, MTD-color, MTD-blurAUROC correlation: r = 0.945No clear effect

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