PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection

arXiv:2404.05231v1 Announce Type: new
Abstract: The vision-language model has brought great improvement to few-shot industrial anomaly detection, which usually needs to design of hundreds of prompts through prompt engineering. For automated scenarios, we first use conventional prompt learning with many-class paradigm as the baseline to automatically learn prompts but found that it can not work well in one-class anomaly detection. To address the above problem, this paper proposes a one-class prompt learning method for few-shot anomaly detection, termed PromptAD. First, …

abstract anomaly anomaly detection arxiv automated class cs.cv design detection engineering few-shot improvement industrial language language model learn learn prompts normal paradigm prompt prompt learning prompts samples through type vision