← Search

Haoyan Guan

2 accepted papers

2024

One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models

CVPR 2024poster

Large pre-trained Vision-Language Models (VLMs) like CLIP despite having remarkable generalization ability are highly vulnerable to adversarial examples. This work studies the adversarial robustness of VLMs from the novel perspective of the text prompt instead of the extensively studied model weight…

2022

Registration Based Few-Shot Anomaly Detection

ECCV 2022poster

"This paper considers few-shot anomaly detection (FSAD), a practical yet under-studied setting for anomaly detection (AD), where only a limited number of normal images are provided for each category at training. So far, existing FSAD studies follow the one-model-per-category learning paradigm used f…