Research map / Label-efficient and robust learning / OOD and anomaly detection
Unsupervised Multi-View Visual Anomaly Detection via Progressive Homography-Guided Alignment
Xintao Chen, Xiaohao Xu, Bozhong Zheng, Yun Liu, Yingna Wu
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 MVAM homography alignment (ablation) | VSAD · RealIAD | S-AUROC: 86.52 -> 94.84 | Improved |
| add MVAM homography alignment (ablation) | VSAD · MANTA | S-AUROC: 84.22 -> 94.52 | Improved |
| add Fusion Refiner Module (ablation) | VSAD · RealIAD | S-AUROC: 93.22 -> 94.84 | Improved |
| add Fusion Refiner Module (ablation) | VSAD · MANTA | S-AUROC: 93.62 -> 94.52 | Improved |
| add 3rd decoder block features to 4th (ablation) | VSAD · RealIAD | S-AUROC: 93.7 -> 94.8 | Improved |
| add 2nd and 1st decoder block features (ablation) | VSAD · RealIAD | S-AUROC: 94.8 -> 89.4 | Hurt |
| increase patch sampling radius from 1x1 to 3x3 (ablation) | VSAD · MANTA | S-AUROC: 91.52 -> 94.52 | Improved |
| increase patch sampling radius from 3x3 to 4x4 (ablation) | VSAD · MANTA | S-AUROC: 94.52 -> 93.95 | Hurt |
Closest papers by meaning
- Align3D-AD: Cross-Modal Feature Alignment and Dual-Prompt Learning for Zero-shot 3D Anomaly Detection (NeurIPS 2026 · similarity 0.89)
- Unveiling Multi-View Anomaly Detection: Intra-view Decoupling and Inter-view Fusion (AAAI 2025 · similarity 0.87)
- Unseen Visual Anomaly Generation (CVPR 2025 · similarity 0.87)
- UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection (CVPR 2025 · similarity 0.87)
- Looking 3D: Anomaly Detection with 2D-3D Alignment (CVPR 2024 · similarity 0.87)
- Odd-One-Out: Anomaly Detection by Comparing with Neighbors (CVPR 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.
