An enhanced SegGPT model with scribble-based prompting auto-labels display defects, reaching about 60 percent coverage with downstream performance comparable to human labels.
Seggpt: Towards segmenting everything in context
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Using In-Context Learning for Automatic Defect Labelling of Display Manufacturing Data
An enhanced SegGPT model with scribble-based prompting auto-labels display defects, reaching about 60 percent coverage with downstream performance comparable to human labels.