AI Paper Atlas

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

Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection

Yuanpeng Tu, Boshen Zhang, Liang Liu, YUXI LI, Jiangning Zhang, Yabiao Wang, Chengjie Wang, cairong zhao

ECCV 2024 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly detection · 33 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 Intra-modal Feature Compactness (IFC) optimization (ablation)LSFA · MVTec-3D AD (RGB+3D)I-AUROC: 0.929 -> 0.959Improved
add Cross-modal Local-to-global Consistency (CLC) alignment (ablation)LSFA · MVTec-3D AD (RGB+3D)I-AUROC: 0.929 -> 0.957Improved
combine IFC and CLC (ablation)LSFA · MVTec-3D AD (RGB+3D)I-AUROC: 0.959 -> 0.971Improved
add global alignment loss L_GA alongside local alignment L_LA (ablation)CLC · MVTec-3D AD (RGB+3D)I-AUROC: 0.949 -> 0.959Improved
add global compactness loss L_GC alongside local L_LC (ablation)IFC · MVTec-3D AD (RGB+3D)I-AUROC: 0.952 -> 0.957Improved
use a single transformer encoder layer adaptor instead of two layers (ablation)LSFA · MVTec-3D AD (RGB+3D)I-AUROC: 0.954 -> 0.974Improved
train adaptors instead of fine-tuning the whole backbone (ablation)LSFA · MVTec-3D AD (RGB+3D)I-AUROC: 84.57 -> 95.42Improved
replace adaptors with LoRA or AdaLoRA (ablation)LSFA · MVTec-3D AD (RGB+3D)I-AUROC: 97.1 -> 93.91Hurt
reduce training data to 5-shot (ablation)LSFA · MVTec-3D AD few-shotI-AUROC: 0.971 -> 0.834Hurt
vary memory bank size and balancing lambda (ablation)LSFA · MVTec-3D ADI-AUROCNo clear effect
LSFA vs AST on RGB-onlyLSFA · MVTec-3D AD (RGB only)I-AUROC mean: 0.880 -> 0.861Hurt
LSFA over M3DM on RGB+3DLSFA · MVTec-3D AD (RGB+3D)I-AUROC mean: 0.945 -> 0.971Improved

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