Research map / Label-efficient and robust learning / OOD and anomaly detection
Learning Unsupervised Metaformer for Anomaly Detection
Jhih-Ciang Wu, Ding-Jie Chen, Chiou-Shann Fuh, Tyng-Luh Liu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add instance-prior generator P to the autoencoder (ablation) | Metaformer autoencoder · MVTec AD (15 categories, pixel-level) | mean PRO: 0.864 -> 0.883 | Improved |
| add transformer to reformulate the instance-prior before multiplication (ablation) | Metaformer (A + P) · MVTec AD (15 categories, pixel-level) | mean PRO: 0.883 -> 0.901 | Improved |
| use the instance-prior (generator and transformer) versus plain autoencoder (ablation) | Metaformer · MVTec AD (15 categories, pixel-level) | mean PRO: improvement from 1.9% to 3.7% mPRO | Improved |
| replace per-category specific models by the universal meta-learned Metaformer versus DifferNet | Metaformer · MVTec AD (15 categories, image-level) | mean AUC: 0.949 -> 0.958 | Improved |
| Metaformer versus DifferNet on MTD | Metaformer · MTD (Magnetic Tile Defects) | mAUC: 0.977 -> 0.993 | Improved |
| Metaformer versus US for localization | Metaformer · MVTec AD (15 categories, pixel-level) | mean PRO: 0.857 -> 0.901 | Improved |
| use meta-learned model with few supporting examples versus DifferNet | Metaformer · MVTec AD (k-shot) | mAUC | Improved |
Closest papers by meaning
- Correcting Deviations from Normality: A Reformulated Diffusion Model for Multi-Class Unsupervised Anomaly Detection (CVPR 2025 · similarity 0.88)
- Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection (CVPR 2025 · similarity 0.87)
- MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning (NeurIPS 2024 · similarity 0.87)
- ResAD: A Simple Framework for Class Generalizable Anomaly Detection (NeurIPS 2024 · similarity 0.87)
- A Diffusion-Based Framework for Multi-Class Anomaly Detection (AAAI 2024 · similarity 0.86)
- RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection (CVPR 2024 · similarity 0.86)
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.
