AI Paper Atlas

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

Registration Based Few-Shot Anomaly Detection

Chaoqin Huang, Haoyan Guan, Aofan Jiang, Ya Zhang, Michael Spratling, Yan-Feng Wang

ECCV 2022 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly detection · 230 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 support set augmentation (ablation)RegAD · MVTec AD image-level, k=2AUC: 79.1 -> 85.7Improved
add support set augmentation (ablation)RegAD · MPDD image-level, k=2/4/8AUC: 1.2%, 0.5%, 0.6%Improved
add feature registration aggregated training across categories (ablation)RegAD · MVTec AD image-level, k=2/4/8AUC: 3.3%, 2.9%, 2.6%Improved
add spatial transformer network (STN) (ablation)RegAD · MVTec AD image-level, k=8AUC: 89.3% to 91.2%Improved
add spatial transformer network (STN) (ablation)RegAD · MPDD image-level, k=8AUC: 64.8% to 71.9%Improved
add spatial transformer network (STN) (ablation)RegAD · MVTec AD pixel-level, k=2AUC: 94.7 -> 94.6No clear effect
use affine STN instead of no STN (ablation)RegAD · MPDD image-level, k=2AUC: 52.8 -> 63.4Improved
use rotation+scale STN instead of no STN (ablation)RegAD · MVTec AD image-level, k=2AUC: 83.0 -> 85.7Improved
aggregated multi-category training instead of individual training (ablation)RegAD · MVTec AD image-level, k=2AUC: 81.5 -> 85.7Improved
add rotation augmentation to support set (individual training) (ablation)RegAD · MVTec AD image-level, k=2AUC: 74.7 -> 79.6Improved
add graying augmentation to support set (individual training) (ablation)RegAD · MVTec AD image-level, k=2AUC: 74.7 -> 74.9No clear effect
add translation augmentation to support set (individual training) (ablation)RegAD · MVTec AD image-level, k=2AUC: 74.7 -> 77.4Improved

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