New DIVE method improves zero-shot anomaly detection with limited data

Researchers have introduced DIVE, a novel approach to zero-shot anomaly detection designed to identify defects in new domains even with limited prior examples of anomalies. DIVE employs a text embedding injection strategy to abstract general anomaly concepts and a disentanglement mechanism to separate visual object semantics from object-agnostic textual prompts. Experiments show DIVE significantly outperforms existing methods on classification and segmentation metrics, particularly in scenarios with scarce auxiliary anomaly data, while maintaining strong performance when diverse anomaly data is available. AI

IMPACT Enhances defect detection capabilities in novel domains with limited prior anomaly data.

RANK_REASON The cluster contains a research paper detailing a new method for anomaly detection. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• alphaXiv
• arXiv
• CatalyzeX Code Finder for Papers
• Connected Papers
• CORE Recommender
• DagsHub
• DIVE
• Gotit.pub
• Hugging Face
• Influence Flower
• Litmaps
• ScienceCast
• scite Smart Citations

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →