Research map / Label-efficient and robust learning / OOD and anomaly detection
A Unified Model for Multi-class Anomaly Detection
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Add one learnable query embedding instead of using no query (ablation) | Transformer reconstruction model · MVTec-AD | Loc. AUROC: 79.4 -> 92.8 | Helped |
| Replace one query embedding with layer-wise query embeddings (ablation) | Transformer reconstruction model · MVTec-AD | Loc. AUROC: 92.8% to 96.5% | Helped |
| Add neighbor masked attention (NMA) (ablation) | 1-query reconstruction model · MVTec-AD | Loc. AUROC: 92.8% to 96.3% | Helped |
| Add feature jittering (FJ) (ablation) | 1-query reconstruction model · MVTec-AD | Loc. AUROC: 92.8% to 95.8% | Helped |
| Add NMA to the layer-wise-query variant (ablation) | Layer-wise-query reconstruction model · MVTec-AD | Loc. AUROC: 96.5 -> 96.5 | No clear effect |
| Add NMA to the layer-wise-query variant (ablation) | Layer-wise-query reconstruction model · MVTec-AD | Det. AUROC: 95.0 -> 95.8 | Helped |
| Add FJ to the layer-wise-query variant (ablation) | Layer-wise-query reconstruction model · MVTec-AD | Loc. AUROC: 96.5 -> 96.2 | Hurt |
| Add FJ to the layer-wise-query variant (ablation) | Layer-wise-query reconstruction model · MVTec-AD | Det. AUROC: 95.0 -> 94.9 | Hurt |
| Combine layer-wise queries, NMA, and FJ (ablation) | Transformer reconstruction model · MVTec-AD | Det. AUROC: 95.0 -> 96.5 | Helped |
| Use UniAD instead of transformer-based competitors | MVTec-AD unified anomaly detection · MVTec-AD unified | Loc. AUROC: 96.8 vs 70.6 | Helped |
Closest papers by meaning
- Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection (CVPR 2025 · similarity 0.90)
- ResAD: A Simple Framework for Class Generalizable Anomaly Detection (NeurIPS 2024 · similarity 0.89)
- AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial Scenarios (CVPR 2025 · similarity 0.88)
- CNC: Cross-modal Normality Constraint for Unsupervised Multi-class Anomaly Detection (AAAI 2025 · similarity 0.88)
- One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detection (NeurIPS 2024 · similarity 0.88)
- A Comprehensive Augmentation Framework for Anomaly Detection (AAAI 2024 · similarity 0.87)
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.