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.
TEACH injects ground-truth labels into the input sequence during training and gradually masks them based on model performance
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 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.