Cross-Lingual Learning in Multilingual Scene Text Recognition
This work addresses the problem of improving text recognition in low-resource languages for multilingual applications, but it is incremental as it tests and refines existing cross-lingual learning concepts.
The paper investigates cross-lingual learning for multilingual scene text recognition, finding that general insights from previous works do not apply, and identifies dataset size of high-resource languages as the crucial condition for improving performance in low-resource languages.
In this paper, we investigate cross-lingual learning (CLL) for multilingual scene text recognition (STR). CLL transfers knowledge from one language to another. We aim to find the condition that exploits knowledge from high-resource languages for improving performance in low-resource languages. To do so, we first examine if two general insights about CLL discussed in previous works are applied to multilingual STR: (1) Joint learning with high- and low-resource languages may reduce performance on low-resource languages, and (2) CLL works best between typologically similar languages. Through extensive experiments, we show that two general insights may not be applied to multilingual STR. After that, we show that the crucial condition for CLL is the dataset size of high-resource languages regardless of the kind of high-resource languages. Our code, data, and models are available at https://github.com/ku21fan/CLL-STR.