MetaWriter uses meta-learned prompt tuning with an image-reconstruction auxiliary task to adapt a handwritten text recognizer to new writers from unlabeled examples, reporting lower error rates on IAM and RIMES with less than 1% of parameters updated.
Handwriting recognition in low-resource scripts using adversarial learn- ing
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
-
MetaWriter: Personalized Handwritten Text Recognition Using Meta-Learned Prompt Tuning
MetaWriter uses meta-learned prompt tuning with an image-reconstruction auxiliary task to adapt a handwritten text recognizer to new writers from unlabeled examples, reporting lower error rates on IAM and RIMES with less than 1% of parameters updated.