Xinyi Gong

VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation

2024 · arXiv (Cornell University)

Recently, large-scale vision-language models such as CLIP have demonstrated immense potential in zero-shot anomaly segmentation (ZSAS) task, utilizing a unified model to directly detect anomalies on any unseen product with painstakingly crafted text prompts. However, …