AI Paper Atlas

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

GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Features

Luc P.J. Sträter, Mohammadreza Salehi, Efstratios Gavves, Cees G.M. Snoek, Yuki M. Asano

ECCV 2024 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly detection · 37 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 GeneralAD (patch-attention discriminator on DINOv2 features) instead of Transformalysemantic and near AD · Aircraft-FGVCimage-level AUROC: 84.0 -> 94.6Improved
use GeneralAD instead of SimpleNet on logical anomaliesindustrial AD · MVTec-LOCOimage-level AUROC: 77.6 -> 84.9Improved
use GeneralAD instead of SimpleNet on MVTec-ADindustrial AD · MVTec-ADimage-level AUROC: 99.6 -> 99.2No clear effect
use GeneralAD instead of FITYMI on Stanford-Carsnear AD · Stanford-Carsimage-level AUROC: 90.8 -> 87.3Hurt
swap DINOv2 backbone for ViT-B/16 in GeneralAD (ablation)GeneralAD · CIFAR-10image-level AUROC: 99.1 -> 93.0Hurt
swap DINOv2 backbone for DINO-B/8 in GeneralAD (ablation)GeneralAD · Aircraft-FGVCimage-level AUROC: 93.4 -> 75.2Hurt
replace backbone of SimpleNet with DINOv2-B (ablation)SimpleNet · MVTec-ADimage-level AUROC: 99.6 -> 97.7Hurt
replace backbone of Transformaly with DINOv2-B (ablation)Transformaly · MVTec-ADimage-level AUROC: 87.9 -> 80.9Hurt
use Noise All Patches instead of Noise Random Patches for semantic data (ablation)GeneralAD · CIFAR-10image-level AUROC: 96.6 -> 99.3Improved
add attention shuffle distortion on semantic data (ablation)GeneralAD · Aircraft-FGVCimage-level AUROC: 94.6 -> 74.5Hurt
add attention shuffle distortion for logical anomalies (ablation)GeneralAD · MVTec-LOCOimage-level AUROC: 84.1 -> 84.9Improved
use Noise Random Patches instead of Noise All Patches for MVTec-AD (ablation)GeneralAD · MVTec-ADimage-level AUROC: 99.0 -> 99.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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