AI Paper Atlas

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

Locally Varying Distance Transform for Unsupervised Visual Anomaly Detection

Wen-Yan Lin, Zhonghang Liu, Siying Liu

ECCV 2022 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly detection · 6 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 instance (layer) normalization to the features (ablation)LVAD and other anomaly detectors · STL-10normality probability separationImproved
increase the number of clusters (local projections) (ablation)LVAD · STL-10 and MNISTaverage AUROCImproved
use ViT features instead of ResNet-50 (ablation)LVAD · STL-10 (20% anomalies)average AUROC: 0.983 -> 0.922Hurt
use SWIN-B features instead of ResNet-50 (ablation)LVAD · STL-10 (20% anomalies)average AUROC: 0.983 -> 0.963Hurt
use SWIN-B features instead of ResNet-50 (ablation)LVAD · MIT-Places-Small (20% anomalies)average AUROC: 0.891 -> 0.899Improved
use ViT features instead of ResNet-50 (ablation)LVAD · MIT-Places-Small (20% anomalies)average AUROC: 0.891 -> 0.870Hurt
move from single-normal to multi-normal class settingLVAD · STL-10average AUROC: 0.986 -> 0.909Hurt
compare LVAD to OC-SVM in multi-normal detectionLVAD · STL-10 multi-normalaverage AUROC: 0.778 -> 0.909Improved
increase anomaly percentage from 0.1% to 30% (performance reversal)Shell-Renormalization · STL-10AUROC: 0.803 -> 0.999Mixed
increase anomaly percentage from 0.1% to 30%OC-SVM · STL-10AUROC: 0.996 -> 0.777Hurt
increase anomaly percentage from 0.1% to 30%LVAD · STL-10AUROC: 0.998 -> 0.977No clear effect
PCA dimension reduction to very low dimension in naive KDE detector (ablation)naive KDE · STL-10 and MNISTAUROCMixed

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