Anomagic: Crossmodal Prompt-driven Zero-shot Anomaly Generation
By: Yuxin Jiang , Wei Luo , Hui Zhang and more
Potential Business Impact:
Creates fake problems to train AI better.
We propose Anomagic, a zero-shot anomaly generation method that produces semantically coherent anomalies without requiring any exemplar anomalies. By unifying both visual and textual cues through a crossmodal prompt encoding scheme, Anomagic leverages rich contextual information to steer an inpainting-based generation pipeline. A subsequent contrastive refinement strategy enforces precise alignment between synthesized anomalies and their masks, thereby bolstering downstream anomaly detection accuracy. To facilitate training, we introduce AnomVerse, a collection of 12,987 anomaly-mask-caption triplets assembled from 13 publicly available datasets, where captions are automatically generated by multimodal large language models using structured visual prompts and template-based textual hints. Extensive experiments demonstrate that Anomagic trained on AnomVerse can synthesize more realistic and varied anomalies than prior methods, yielding superior improvements in downstream anomaly detection. Furthermore, Anomagic can generate anomalies for any normal-category image using user-defined prompts, establishing a versatile foundation model for anomaly generation.
Similar Papers
Beyond Human-prompting: Adaptive Prompt Tuning with Semantic Alignment for Anomaly Detection
CV and Pattern Recognition
Finds weird things in pictures automatically.
CHIMERA: Adaptive Cache Injection and Semantic Anchor Prompting for Zero-shot Image Morphing with Morphing-oriented Metrics
CV and Pattern Recognition
Makes pictures smoothly change between two things.
AnoStyler: Text-Driven Localized Anomaly Generation via Lightweight Style Transfer
CV and Pattern Recognition
Creates realistic fake defects for better quality checks.