Model card
AnomalyGPT.
CASIA / UCASopen-sourceLarge Vision-Language Model (LLaMA + ImageBind)
First LLM-based industrial anomaly detection model; eliminates manual threshold setting. AAAI 2024.
§ 01 · Benchmarks
Every benchmark AnomalyGPT has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | MVTec AD | Industrial Inspection · Anomaly Detection | auroc | 97.4% | #9 | 2023-08-29 | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area
Where AnomalyGPT actually performs.
§ 03 · Papers
1 paper with results for AnomalyGPT.
- 2023-08-29· 1 result
AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
1
result
1 of 1 rows marked verified.