AnomalyControl: Learning Cross-modal Semantic Features for Controllable
Anomaly Synthesis
AnomalyControl: Learning Cross-modal Semantic Features for Controllable
Anomaly Synthesis
Anomaly synthesis is a crucial approach to augment abnormal data for advancing anomaly inspection. Based on the knowledge from the large-scale pre-training, existing text-to-image anomaly synthesis methods predominantly focus on textual information or coarse-aligned visual features to guide the entire generation process. However, these methods often lack sufficient descriptors to …