Research map / Label-efficient and robust learning / OOD and anomaly detection
One-for-All: Proposal Masked Cross-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 |
|---|---|---|---|
| Use patch-level reconstruction to adapt to unseen classes | PMAD · MVTecAD and BTAD cross-class | image-level AUROC | Helped |
| Use ViT structure instead of asymmetric architecture (ablation) | PMAD · MVTecAD multi-class | image-level AUROC: 0.918 -> 0.945 | Helped |
| Combine random, blockwise, and other masking strategies during training (ablation) | PMAD · MVTecAD multi-class | image-level AUROC: 0.929 -> 0.945 | Helped |
| Use visual tokens instead of raw pixels as the reconstruction objective (ablation) | PMAD · MVTecAD multi-class | image-level AUROC: 0.773 -> 0.945 | Helped |
| Use visual tokens instead of deep features as the reconstruction objective (ablation) | PMAD · MVTecAD multi-class | image-level AUROC: 0.844 -> 0.945 | Helped |
| Use prototype-guided proposal masking instead of random masking at inference (ablation) | PMAD · MVTecAD multi-class | image-level AUROC: 0.730 -> 0.945 | Helped |
| Use prototype-guided proposal masking instead of blockwise masking at inference (ablation) | PMAD · MVTecAD multi-class | image-level AUROC: 0.749 -> 0.945 | Helped |
| Use blockwise rather than random masking during training (ablation) | PMAD · MVTecAD multi-class | image-level AUROC: 0.929 -> 0.939 | Helped |
Closest papers by meaning
- Long-Tailed Anomaly Detection with Learnable Class Names (CVPR 2024 · similarity 0.88)
- AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial Scenarios (CVPR 2025 · similarity 0.87)
- Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection (CVPR 2025 · similarity 0.87)
- A Diffusion-Based Framework for Multi-Class Anomaly Detection (AAAI 2024 · similarity 0.87)
- ResAD: A Simple Framework for Class Generalizable Anomaly Detection (NeurIPS 2024 · similarity 0.87)
- CNC: Cross-modal Normality Constraint for Unsupervised Multi-class Anomaly Detection (AAAI 2025 · 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.