Using In-Context Learning for Automatic Defect Labelling of Display Manufacturing Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hussain, Babar, Liu, Qiang, Chen, Gang, She, Bihai, Yu, Dahai
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916781004685312
author Hussain, Babar
Liu, Qiang
Chen, Gang
She, Bihai
Yu, Dahai
author_facet Hussain, Babar
Liu, Qiang
Chen, Gang
She, Bihai
Yu, Dahai
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_04717
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Using In-Context Learning for Automatic Defect Labelling of Display Manufacturing Data
Hussain, Babar
Liu, Qiang
Chen, Gang
She, Bihai
Yu, Dahai
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
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.
title Using In-Context Learning for Automatic Defect Labelling of Display Manufacturing Data
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2506.04717