7 papers
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…
MuSc-V2: Zero-Shot Multimodal Industrial Anomaly Classification and Segmentation with Mutual Scoring of Unlabeled Samples
Xurui Li, Feng Xue, Yu Zhou
Zero-shot anomaly classification (AC) and segmentation (AS) methods aim to identify and outline defects without using any labeled samples. In this paper, we reveal a key property t…
AnoRefiner: Anomaly-Aware Group-Wise Refinement for Zero-Shot Industrial Anomaly Detection
Dayou Huang, Feng Xue, Xurui Li +1
Zero-shot industrial anomaly detection (ZSAD) methods typically yield coarse anomaly maps as vision transformers (ViTs) extract patch-level features only. To solve this, recent sol…
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…
RoBiS: Robust Binary Segmentation for High-Resolution Industrial Images
Xurui Li, Zhonesheng Jiang, Tingxuan Ai +1
Robust unsupervised anomaly detection (AD) in real-world scenarios is an important task. Current methods exhibit severe performance degradation on the MVTec AD 2 benchmark due to i…