8 papers
DeltaDeno: Zero-Shot Anomaly Generation via Delta-Denoising Attribution
Chaoran Xu, Chengkan Lv, Qiyu Chen +3
Anomaly generation is often framed as few-shot fine-tuning with anomalous samples, which contradicts the scarcity that motivates generation and tends to overfit category priors. We…
CoPS: Conditional Prompt Synthesis for Zero-Shot Anomaly Detection
Qiyu Chen, Zhen Qu, Wei Luo +7
Recently, large pre-trained vision-language models have shown remarkable performance in zero-shot anomaly detection (ZSAD). With fine-tuning on a single auxiliary dataset, the mode…
MRAD: Zero-Shot Anomaly Detection with Memory-Driven Retrieval
Chaoran Xu, Chengkan Lv, Qiyu Chen +2
Zero-shot anomaly detection (ZSAD) often leverages pretrained vision or vision-language models, but many existing methods use prompt learning or complex modeling to fit the data di…
Anomagic: Crossmodal Prompt-driven Zero-shot Anomaly Generation
Yuxin Jiang, Wei Luo, Hui Zhang +4
We propose Anomagic, a zero-shot anomaly generation method that produces semantically coherent anomalies without requiring any exemplar anomalies. By unifying both visual and textu…
INP-Former++: Advancing Universal Anomaly Detection via Intrinsic Normal Prototypes and Residual Learning
Wei Luo, Haiming Yao, Yunkang Cao +4
Anomaly detection (AD) is essential for industrial inspection and medical diagnosis, yet existing methods typically rely on ``comparing'' test images to normal references from a tr…
Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detection
Zhen Qu, Xian Tao, Xinyi Gong +5
Recently, vision-language models (e.g. CLIP) have demonstrated remarkable performance in zero-shot anomaly detection (ZSAD). By leveraging auxiliary data during training, these mod…