Zhuo Xu, Xiang Xiang

Anvita Agarwal Srinivas, Tuomas Oikarinen, Divyansh Srivastava +2

Yanning Hou, Peiyuan Li, Zirui Liu +4

Zero-shot anomaly detection (ZSAD) requires detecting and localizing anomalies without access to target-class anomaly samples. Mainstream methods rely on vision-language models (VLMs) such as CLIP: they build hand-crafted or learned prompt sets for normal and abnormal semantics, then compute image-text similarities for open-set discrimination. While effective, this paradigm depends on a text encoder and cross-modal alignment, which can lead to training instability and parameter redundancy. This work revisits the necessity of the text branch in ZSAD and presents VisualAD, a purely visual framew

Fuyun Wang, Tong Zhang, Yuanzhi Wang +4

Tsai-Shien Chen, Aliaksandr Siarohin, Willi Menapace +7

Xiaokun Li, Yaping Huang, Qingji Guan