Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Zero-Shot Anomaly Detection via Batch Normalization
Aodong Li, Chen Qiu, Marius Kloft, Padhraic Smyth, Maja Rudolph, Stephan Mandt
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 |
|---|---|---|---|
| Use ACR-DSVDD instead of CLIP-AD | Zero-shot image anomaly detection · CIFAR100-C Gaussian noise, 1% anomalies | AUC (%): 82.3$\pm$1.1 -> 87.7$\pm$1.4 | Improved |
| Use ACR-BCE instead of OC-MAML | Zero-shot image anomaly detection · OrganA, 1% anomalies | AUC (%): 73.7$\pm$4.7 -> 81.1$\pm$0.8 | Improved |
| Use ACR instead of WinCLIP | Zero-shot anomaly segmentation · MVTec AD | pixel-level AUC (%): 85.1$\pm$0.0 -> 92.5$\pm$0.2 | Improved |
| Use ACR instead of WinCLIP | Zero-shot image-level anomaly detection · MVTec AD | image-level AUC (%): 91.8$\pm$0.0 -> 85.8$\pm$0.6 | Hurt |
| Use ACR-NTL instead of OC-SVM | Zero-shot tabular anomaly detection · Anoshift FAR, 1% anomalies | AUC (%): 49.6$\pm$0.2 -> 62.5$\pm$0.2 | Improved |
| Use ACR-DSVDD instead of KNN | Zero-shot tabular anomaly detection · Anoshift AVG, 1% anomalies | AUC (%): 70.8$\pm$0.1 -> 74.0$\pm$0.2 | Improved |
| Use Meta Outlier Exposure rather than one-class classification loss (ablation) | ACR for image anomaly detection · Two image datasets | AUC | Improved |
| Use Meta Outlier Exposure rather than fine-tuned ResNet152 (ablation) | ACR for image anomaly detection · Two image datasets | AUC | Improved |
| Use images from other classes as example anomalies during training (ablation) | ACR anomaly segmentation · MVTec AD | AUC | Improved |
| Train using batch normalization (ablation) | ACR · Zero-shot anomaly detection | AUC | Mixed |
Closest papers by meaning
- DZAD: Diffusion-based Zero-shot Anomaly Detection (AAAI 2025 · similarity 0.88)
- One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detection (NeurIPS 2024 · similarity 0.87)
- Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models (CVPR 2025 · similarity 0.87)
- ADPretrain: Advancing Industrial Anomaly Detection via Anomaly Representation Pretraining (NeurIPS 2025 · similarity 0.87)
- AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial Scenarios (CVPR 2025 · similarity 0.87)
- Aligning and Prompting Anything for Zero-Shot Generalized 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.
