AI Paper Atlas

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

SoftPatch: Unsupervised Anomaly Detection with Noisy Data

Jiang Xi, Jianlin Liu, Jinbao Wang, Qiang Nie, Kai WU, Yong Liu, Chengjie Wang, Feng Zheng

NeurIPS 2022 · Label-efficient and robust learning › OOD and anomaly detection · approach: Anomaly detection with contaminated data · 21 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 LOF noise discriminator before coreset selection (ablation)SoftPatch · MVTecAD-noise-0.1 overlappixel AUROC: 0.693 -> 0.963Improved
add LOF noise discriminator before coreset selection (ablation)SoftPatch · MVTecAD-noise-0.1 overlapimage AUROC: 0.685 -> 0.984Improved
add soft weight re-weighting to LOF (ablation)SoftPatch · MVTecAD-noise-0.1 overlappixel AUROC: 0.963 -> 0.969Improved
add soft weight re-weighting to LOF (ablation)SoftPatch · MVTecAD-noise-0.1 overlapimage AUROC: 0.984 -> 0.982No clear effect
add soft weight to nearest discriminator (ablation)SoftPatch · MVTecAD-noise-0.1 overlappixel AUROC: 0.944 -> 0.958Improved
add soft weight to Gaussian discriminator (ablation)SoftPatch · MVTecAD-noise-0.1 no overlapimage AUROC: 0.927 -> 0.922No clear effect
use LOF instead of nearest/Gaussian discriminator (ablation)SoftPatch · MVTecAD-noise-0.1 overlapimage AUROC: 0.966/0.925 -> 0.984Improved
use LOF-K >= 6 instead of small K (3) (ablation)SoftPatch · MVTecAD overlappixel AUROC: 0.955 -> 0.975Improved
increase removal threshold tau toward 0.15 (ablation)SoftPatch · MVTecAD overlapimage/pixel AUROCImproved
use SoftPatch-LOF instead of PatchCore under noiseSoftPatch · MVTecAD-noise-0.1 overlappixel AUROC: 0.654 -> 0.969Improved
use SoftPatch instead of PatchCore with no added noiseSoftPatch · BTAD meanimage AUROC: 0.957 -> 0.977Improved
use random instead of greedy coreset sampling in PatchCoreSoftPatch · MVTecAD-noise-0.1 no overlapimage AUROC: 0.984 -> 0.896Hurt

Later papers that compared with this method

4 later accepted papers report SoftPatch as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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