CVPR2025

AA-CLIP: Enhancing Zero-Shot Anomaly Detection via Anomaly-Aware CLIP

Wenxin Ma, Xu Zhang, Qingsong Yao, Fenghe Tang, Chenxu Wu, Yingtai Li, Rui Yan, Zihang Jiang, S. Kevin Zhou

Abstract

ner, achieving effective AD while maintaining CLIP's class knowledge. Extensive experiments validate AA-CLIP as a resource-efficient solution for zero-shot AD tasks, achieving state-of-the-art results in industrial and medical applications. The code is available at https://github. com/Mwxinnn/AA-CLIP .