4 papers
Focus and Supplement: Dual-Enhanced Vision Transformer for Multi-Class Anomaly Classification
Xurui Li, Enjie Xu, Chenzhou Li +4
Multi-class anomaly classification in industrial vision remains challenging due to noisy/incomplete anomaly representations and the unknown number of anomaly classes. To overcome t…
DeCo: Zero-Shot Industrial Anomaly Generation through Decoupling and Recoupling
Shilei Zeng, Xurui Li, Yaohan Tang +1
Industrial anomaly inspection is severely hindered by the scarcity of real anomalous data. Zero-shot industrial anomaly generation addresses this by generating anomalies on specifi…
UniScale: Arbitrary-Scale Industrial Anomaly Generation
Shilei Zeng, Linxin Guan, Xurui Li +2
Industrial anomaly inspection faces a major challenge due to the lack of real-world anomaly samples. While generative models are used to create anomaly data, existing methods still…
SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuning
Zhewei Dai, Shilei Zeng, Haotian Liu +3
We introduce SeaS, a unified industrial generative model for automatically creating diverse anomalies, authentic normal products, and precise anomaly masks. While extensive researc…