Research map / Label-efficient and robust learning / OOD and anomaly detection
Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection
Check 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 |
|---|---|---|---|
| Add SSPCAB to DRAEM | DRAEM · MVTec AD | detection AUROC: 98.0 -> 98.9 | Helped |
| Add SSPCAB to DRAEM | DRAEM · MVTec AD | localization AP: 68.4% to 69.9% | Helped |
| Add SSPCAB to DRAEM | DRAEM · MVTec AD | localization AUROC: 97.3 -> 97.2 | Hurt |
| Add SSPCAB to CutPaste 3-way | CutPaste 3-way · MVTec AD | detection AUROC: 95.2 -> 96.1 | Helped |
| Add SSPCAB to Liu CVPR 2018 | Liu CVPR 2018 · Avenue | RBDC: 19.59 -> 20.13 | Helped |
| Add SSPCAB to Liu ICCV 2021 | Liu ICCV 2021 · Avenue | RBDC: 41.05 -> 62.27 | Helped |
| Add SSPCAB to Georgescu TPAMI 2021 | Georgescu TPAMI 2021 · Avenue | TBDC: 66.85 -> 64.91 | Hurt |
| Add SSPCAB to Georgescu TPAMI 2021 | Georgescu TPAMI 2021 · ShanghaiTech | RBDC: 41.34 -> 40.55 | Hurt |
| Use MSE instead of MAE for the SSPCAB reconstruction loss (ablation) | Plain auto-encoder + SSPCAB · Avenue | Micro AUC: 83.9 -> 84.2 | Helped |
| Use channel attention rather than no attention (ablation) | Plain auto-encoder + masked convolution · Avenue | Micro AUC: 84.2 -> 85.9 | Helped |
| Use spatial attention instead of channel attention (ablation) | Plain auto-encoder + SSPCAB · Avenue | Micro AUC: 85.9 -> 84.3 | Hurt |
| Set channel-attention reduction ratio to 4 instead of 8 (ablation) | Plain auto-encoder + SSPCAB · Avenue | Micro AUC: 85.9 -> 85.6 | Hurt |
Closest papers by meaning
- Attention-Conditioned Augmentations for Self-Supervised Anomaly Detection and Localization (AAAI 2023 · similarity 0.88)
- FrameShield: Adversarially Robust Video Anomaly Detection (NeurIPS 2025 · similarity 0.86)
- A Comprehensive Augmentation Framework for Anomaly Detection (AAAI 2024 · similarity 0.86)
- Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors (CVPR 2024 · similarity 0.86)
- Long-Tailed Anomaly Detection with Learnable Class Names (CVPR 2024 · similarity 0.85)
- A Diffusion-Based Framework for Multi-Class Anomaly Detection (AAAI 2024 · 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.