Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detection
Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detection
Current zero-shot anomaly detection (ZSAD) methods show remarkable success in prompting large pre-trained vision-language models to detect anomalies in a target dataset without using any dataset-specific training or demonstration. However, these methods are often focused on crafting/learning prompts that capture only coarse-grained semantics of abnormality, e.g., high-level semantics like "damaged", …