Guiguang Ding

Transductive Zero-Shot Recognition via Shared Model Space Learning

2016 · Proceedings of the AAAI Conference on Artificial Intelligence

Zero-shot Recognition (ZSR) is to learn recognition models for novel classes without labeled data. It is a challenging task and has drawn considerable attention in recent years. The basic idea is to transfer knowledge from …

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, …