AnomalyCLIP: Object-agnostic prompt learning for zero-shot anomaly detection

• Main Authors: ZHOU, Qihang, PANG, Guansong, TIAN, Yu, HE, Shibo, CHEN, Jiming
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Anomaly detection; Zero-shot anomaly detection; CLIP; Industrial defect inspection; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/9279; https://ink.library.smu.edu.sg/context/sis_research/article/10279/viewcontent/9222_AnomalyCLIP_Object_agnost.pdf
• Institution: Singapore Management University

Zero-shot anomaly detection (ZSAD) requires detection models trained using auxiliary data to detect anomalies without any training sample in a target dataset. It is a crucial task when training data is not accessible due to various concerns, e.g., data privacy, yet it is challenging since the models...