Research map / Label-efficient and robust learning / OOD and anomaly detection
Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection
Neelu Madan, Nicolae-Cătălin Ristea, Radu Tudor Ionescu, Kamal Nasrollahi, Fahad Shahbaz Khan, Thomas Baltzer Moeslund, Mubarak Shah
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 SSMCTB block | NSA · BRATS | detection AUROC (%): 53.66 -> 60.09 | Improved |
| add SSMCTB block | DRAEM · BRATS | detection AUROC (%): 41.06 -> 50.27 | Improved |
| add 3D SSMCTB to 3D DRAEM | 3D DRAEM · BRATS | detection AUROC (%): 43.74 -> 53.70 | Improved |
| add SSMCTB instead of SSPCAB | DRAEM · BRATS | detection AUROC (%): 44.19 -> 50.27 | Improved |
| add SSMCTB block | DRAEM · MVTec AD | detection AUROC (%): 98.0 -> 98.7 | Improved |
| add SSMCTB block | DRAEM · MVTec AD | localization AP (%): 68.4 -> 70.5 | Improved |
| add SSMCTB block | DRAEM · MVTec AD | localization AUROC (%): 97.3 -> 97.2 | No clear effect |
| add SSMCTB block | Liu et al. (future frame prediction) · Avenue | micro AUC (%): 85.1 -> 89.5 | Improved |
| add SSMCTB block | Park et al. · Avenue | micro AUC (%): 82.8 -> 87.0 | Improved |
| add SSMCTB block | Georgescu et al. · Avenue | micro AUC (%): 92.3 -> 93.2 | Improved |
| add SSMCTB block | Park et al. · Thermal Rare Event | micro AUC (%): 53.2 -> 58.9 | Improved |
| add 3D SSMCTB | Barbalau et al. · Avenue | micro AUC (%): 91.6 -> 91.6 | No clear effect |
Closest papers by meaning
- Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection (CVPR 2022 · similarity 0.95)
- A Diffusion-Based Framework for Multi-Class Anomaly Detection (AAAI 2024 · similarity 0.86)
- AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial Scenarios (CVPR 2025 · similarity 0.86)
- Long-Tailed Anomaly Detection with Learnable Class Names (CVPR 2024 · similarity 0.86)
- Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors (CVPR 2024 · similarity 0.85)
- OmiAD: One-Step Adaptive Masked Diffusion Model for Multi-class Anomaly Detection via Adversarial Distillation (ICML 2025 · similarity 0.85)
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.
