Zero and few-shot industrial image anomaly detection framework comparing AnomalyDINO & MuSc models across MVTec AD, BTAD, and ViSA datasets with MLflow tracking and flexible configuration.
computer-vision pytorch hydra zero-shot-learning anomaly-detection musc defect-detection few-shot-learning industrial-ai mlflow anomalydino
-
Updated
Jul 13, 2025 - Jupyter Notebook