AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

Remembering Normality: Memory-guided Knowledge Distillation for Unsupervised Anomaly Detection

Zhihao Gu, Liang Liu, Xu Chen, Ran Yi, Jiangning Zhang, Yabiao Wang, Chengjie Wang, Annan Shu, Guannan Jiang, Lizhuang Ma

ICCV 2023 · Label-efficient and robust learning › Knowledge distillation · approach: Distillation with causal and adaptive guidance · 83 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 NR Memory with orthogonal loss to RD (ablation)RD baseline · MVTec ADImage AUROC: 98.4 -> 98.7Improved
add normality memorization loss L_NM to NR Memory (ablation)RD with NR Memory · MVTec ADImage AUROC: 98.7 -> 99.1Improved
combine NR Memory, L_Orth and L_NM (ablation)RD baseline · MVTec ADImage AUROC: 98.4 -> 99.6Improved
increase memory items from 0 to 50 per stage (ablation)MemKD · MVTec ADImage AUROC: 98.9 -> 99.6Improved
increase memory items from 50 to 100 per stage (ablation)MemKD · MVTec ADImage AUROC: 99.6 -> 99.4Hurt
apply NR Memory to forward distillation (MKD) (ablation)MKD · MVTec ADImage AUROC: 97.5 -> 98.7Improved
use NR Memory with normality embedding learning instead of MemAE memory (ablation)RD baseline · MPDDPixel PRO: 86.2 -> 94.9Improved
NR Memory adds storage and time over RDRD baseline · MPDDmemory / inference time: 0.0M -> 0.3M; 0.31s -> 0.33sHurt
MemKD versus PatchCore on pixel AUROCMemKD · VisAPixel AUROC: 98.8 -> 98.4Hurt

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