Feeding ground-truth label embeddings into an STR decoder and progressively masking them based on training loss improves accuracy on several benchmarks while leaving inference unchanged.
TYPO” as “TYPE
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
-
TEACH: Text Encoding as Curriculum Hints for Scene Text Recognition
Feeding ground-truth label embeddings into an STR decoder and progressively masking them based on training loss improves accuracy on several benchmarks while leaving inference unchanged.