Research map / Label-efficient and robust learning / OOD and anomaly detection
Anomaly Detection and Generation with Diffusion Models: A Survey
Yang Liu, Jing Liu, Chengfang Li, Rui Xi, Wenchao Li, Liang Cao, Jin Wang, Laurence Tianruo Yang, Junsong Yuan, Wei Zhou
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 diffusion-based DMAD instead of RTFM for video anomaly detection | video AD · UCSD Ped2 | AUC: 96.3 -> 99.7 | Improved |
| use DMAD instead of RTFM on CUHK Avenue | video AD · CUHK Avenue | AUC: 85.1 -> 92.8 | Improved |
| use diffusion-based VADiffusion instead of RTFM | video AD · ShanghaiTech | AUC: 73 -> 71.7 | Hurt |
| use SensitiveHUE instead of TranAD for time series AD | time series AD · SWaT | F1: 74.16 -> 91.08 | Improved |
| use SensitiveHUE instead of TranAD | time series AD · MSL | point-adjusted F1: 94.94 -> 98.42 | Improved |
| use SensitiveHUE instead of NPSR | time series AD · WADI | F1: 61.31 -> 69.96 | Improved |
| report point-adjusted F1 instead of plain F1 for AnomalyTran on SWaT | AnomalyTran · SWaT | F1 vs F1_PA: 21.43 -> 94.07 | Mixed |
| use AutoUAD instead of NeuTraLAD for tabular AD | tabular AD · 47 tabular datasets (avg) | AUC (%): 71.45 -> 92.68 | Improved |
| use DPAD instead of SCAD | tabular AD · 47 tabular datasets (avg) | AUC (%): 69.15 -> 88.05 | Improved |
| use specialized DNN instead of AutoUAD | tabular AD · 47 tabular datasets (avg) | AUC (%): 92.68 -> 92.27 | No clear effect |
| use GLAD instead of Tebbe et al. | image AD · VisA | I-AUROC: 96.0 -> 99.5 | Improved |
| use Tebbe et al. instead of PatchCore | image AD · BTAD | PRO: 92.7 -> 95.2 | Improved |
Closest papers by meaning
- On Diffusion Modeling for Anomaly Detection (ICLR 2024 · similarity 0.92)
- OmiAD: One-Step Adaptive Masked Diffusion Model for Multi-class Anomaly Detection via Adversarial Distillation (ICML 2025 · similarity 0.90)
- DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detector (ICLR 2025 · similarity 0.89)
- The Elephant in the Room: Towards A Reliable Time-Series Anomaly Detection Benchmark (NeurIPS 2024 · similarity 0.88)
- Generating and Reweighting Dense Contrastive Patterns for Unsupervised Anomaly Detection (AAAI 2024 · similarity 0.88)
- We Need to Rethink Benchmarking in Anomaly Detection (NeurIPS 2026 · similarity 0.88)
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.
