Using In-Context Learning for Automatic Defect Labelling of Display Manufacturing Data
This provides a practical solution for reducing manual annotation efforts in industrial inspection systems for display manufacturing.
The paper tackles the problem of manual annotation for display panel defect detection by developing an AI-assisted auto-labeling system using in-context learning, which achieves an average IoU increase of 0.22 and a 14% recall improvement while maintaining 60% auto-labeling coverage.
This paper presents an AI-assisted auto-labeling system for display panel defect detection that leverages in-context learning capabilities. We adopt and enhance the SegGPT architecture with several domain-specific training techniques and introduce a scribble-based annotation mechanism to streamline the labeling process. Our two-stage training approach, validated on industrial display panel datasets, demonstrates significant improvements over the baseline model, achieving an average IoU increase of 0.22 and a 14% improvement in recall across multiple product types, while maintaining approximately 60% auto-labeling coverage. Experimental results show that models trained on our auto-labeled data match the performance of those trained on human-labeled data, offering a practical solution for reducing manual annotation efforts in industrial inspection systems.